CN111241209A - Method and apparatus for generating information - Google Patents
Method and apparatus for generating information Download PDFInfo
- Publication number
- CN111241209A CN111241209A CN202010005728.9A CN202010005728A CN111241209A CN 111241209 A CN111241209 A CN 111241209A CN 202010005728 A CN202010005728 A CN 202010005728A CN 111241209 A CN111241209 A CN 111241209A
- Authority
- CN
- China
- Prior art keywords
- text
- word sequence
- relation
- vector
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/288—Entity relationship models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The embodiment of the application discloses a method and a device for generating information, and belongs to the fields of computer technology and knowledge graph. One embodiment of the method comprises: acquiring a main body relation binary group and a text, wherein the main body relation binary group comprises a main body and a relation; segmenting the text into a sequence of text words; inputting the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, wherein the slot filling model is used for labeling objects in the text word sequence; and generating a subject relation object triple based on the subject relation binary group and the labeling result, wherein the subject relation object triple comprises a subject, a relation and an object of the text. This embodiment improves the object recognition accuracy.
Description
Technical Field
The embodiment of the application relates to the technical field of computers, in particular to a method and a device for generating information.
Background
The knowledge graph is a large-scale knowledge base of real world knowledge represented in a structured form from the semantic perspective, and is a directed graph, wherein the directed graph comprises elements such as entities (nodes) and relations (edges). The SPO (Subject prediction Object) triple is also called a Subject relationship Object triple, and refers to a triple formed by an entity pair (S and O) and a relationship (P) therebetween. From the perspective of knowledge graph construction, the entity relationship extraction can obtain the relationship attribute value of entity missing, so that the connectivity of the knowledge graph is improved, and the knowledge richness and completeness of the knowledge graph are efficiently improved.
At present, a commonly used entity extraction method is to convert a subject relationship binary into a question, and input the question and a text into a reading understanding model, where the reading understanding model marks a start position and an end position of an object in the text. However, the reading understanding model actually degenerates the subject relationship into a problem, loses structural information, and affects the object recognition effect.
Disclosure of Invention
The embodiment of the application provides a method and a device for generating information.
In a first aspect, an embodiment of the present application provides a method for generating information, where a principal relation binary group and a text are obtained, where the principal relation binary group includes a principal and a relation; segmenting the text into a sequence of text words; inputting the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, wherein the slot filling model is used for labeling objects in the text word sequence; and generating a subject relation object triple based on the subject relation binary group and the labeling result, wherein the subject relation object triple comprises a subject, a relation and an object of the text.
In some embodiments, the slot-filling model includes an input layer, a positioning layer, an embedding layer, an encoding layer, a decoding layer, and an output layer.
In some embodiments, inputting the principal relationship binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, including: inputting the main body relation binary group and the text word sequence into an input layer to obtain word sequence characteristics and distance characteristics; inputting the distance characteristics into a positioning layer to obtain position information; inputting the word sequence characteristics and the position information into an embedding layer to obtain a word sequence vector and a position vector; inputting the word sequence vector into a coding layer to obtain a coding vector; inputting the position vector and the coding vector into a decoding layer to obtain a decoding vector; and inputting the decoding vector to an output layer to obtain a labeling result.
In some embodiments, the encoding layer includes a first bidirectional long-short term memory network, and the decoding layer includes a location attention module, a relationship attention module, and a second bidirectional long-short term memory network.
In some embodiments, inputting the position vector and the encoded vector to a decoding layer to obtain a decoded vector, comprises: splicing the position vector and the coding vector and inputting the spliced position vector and the coding vector into a position attention module to obtain position information of a word distance main body and a relation in a text word sequence; inputting the long and short term memory network coding and coding vector of the relation to a relation attention module to obtain semantic similarity between words and relations in the text word sequence; and inputting the coding vector, the position information of the word distance main body and the relation in the text word sequence and the semantic similarity of the words and the relation in the text word sequence into a second bidirectional long-short term memory network to obtain a decoding vector.
In some embodiments, inputting the decoding vector to the output layer to obtain the labeling result, including: performing multi-classification on decoding vectors of words in the text word sequence through an activation function to obtain the probability that the words in the text word sequence belong to each of multiple categories, wherein the multi-classification is to calculate the probability that the words belong to each of the multiple categories; and labeling the text word sequence based on the category corresponding to the maximum probability of the words in the text word sequence to generate a labeling result.
In some embodiments, the word sequence features include at least one of: the method comprises the following steps of (1) a text word sequence, a part of speech sequence of the text word sequence, a named entity recognition sequence of the text word sequence and a relation word sequence of a relation, wherein distance characteristics comprise at least one of the following items: the distance from a word in the sequence of text words to the subject, and the distance from a word in the sequence of text words to the relationship.
In some embodiments, the slot filling model labels the sequence of text words in a biees sequence labeling manner.
In a second aspect, an embodiment of the present application provides an apparatus for generating information, including: an acquisition unit configured to acquire a subject relationship binary group and a text, wherein the subject relationship binary group includes a subject and a relationship; a segmentation unit configured to segment the text into a sequence of text words; the labeling unit is configured to input the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, wherein the slot filling model is used for labeling objects in the text word sequence; and the generating unit is configured to generate a subject relation object triple based on the subject relation binary group and the labeling result, wherein the subject relation object triple comprises a subject, a relation and an object of the text.
In some embodiments, the slot-filling model includes an input layer, a positioning layer, an embedding layer, an encoding layer, a decoding layer, and an output layer.
In some embodiments, the annotation unit comprises: the input subunit is configured to input the subject relation binary group and the text word sequence into the input layer to obtain a word sequence characteristic and a distance characteristic; a positioning subunit configured to input the distance features into a positioning layer, resulting in position information; the embedding subunit is configured to input the word sequence characteristics and the position information into the embedding layer to obtain a word sequence vector and a position vector; an encoding subunit configured to input the word sequence vector to an encoding layer, resulting in an encoded vector; a decoding subunit configured to input the position vector and the encoded vector to a decoding layer, resulting in a decoded vector; and the output subunit is configured to input the decoding vector to the output layer to obtain the labeling result.
In some embodiments, the encoding layer includes a first bidirectional long-short term memory network, and the decoding layer includes a location attention module, a relationship attention module, and a second bidirectional long-short term memory network.
In some embodiments, the encoding subunit is further configured to: splicing the position vector and the coding vector and inputting the spliced position vector and the coding vector into a position attention module to obtain position information of a word distance main body and a relation in a text word sequence; inputting the long and short term memory network coding and coding vector of the relation to a relation attention module to obtain semantic similarity between words and relations in the text word sequence; and inputting the coding vector, the position information of the word distance main body and the relation in the text word sequence and the semantic similarity of the words and the relation in the text word sequence into a second bidirectional long-short term memory network to obtain a decoding vector.
In some embodiments, the output subunit is further configured to: performing multi-classification on decoding vectors of words in the text word sequence through an activation function to obtain the probability that the words in the text word sequence belong to each of multiple categories, wherein the multi-classification is to calculate the probability that the words belong to each of the multiple categories; and labeling the text word sequence based on the category corresponding to the maximum probability of the words in the text word sequence to generate a labeling result.
In some embodiments, the word sequence features include at least one of: the method comprises the following steps of (1) a text word sequence, a part of speech sequence of the text word sequence, a named entity recognition sequence of the text word sequence and a relation word sequence of a relation, wherein distance characteristics comprise at least one of the following items: the distance from a word in the sequence of text words to the subject, and the distance from a word in the sequence of text words to the relationship.
In some embodiments, the slot filling model labels the sequence of text words in a biees sequence labeling manner.
In a third aspect, an embodiment of the present application provides an electronic device, including: one or more processors; a storage device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described in any implementation of the first aspect.
In a fourth aspect, the present application provides a computer-readable medium, on which a computer program is stored, which, when executed by a processor, implements the method as described in any implementation manner of the first aspect.
According to the method and the device for generating the information, the principal relation binary group and the text are firstly obtained; then cutting the text into text word sequences; then, inputting the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence; and finally, generating a subject relation object triple based on the subject relation binary group and the labeling result. The object is identified based on the slot filling model, the sum structure of the main body and the relation is reserved, and the object identification accuracy is improved.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
FIG. 1 is an exemplary system architecture to which the present application may be applied;
FIG. 2 is a flow diagram of one embodiment of a method for generating information according to the present application;
FIG. 3 is a flow diagram of yet another embodiment of a method for generating information according to the present application;
FIG. 4 shows a schematic structural diagram of a slot-fill model;
FIG. 5 is a schematic block diagram illustrating one embodiment of an apparatus for generating information according to the present application;
FIG. 6 is a schematic block diagram of a computer system suitable for use in implementing an electronic device according to embodiments of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be noted that, for convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 shows an exemplary system architecture 100 to which embodiments of the method for generating information or the apparatus for generating information of the present application may be applied.
As shown in fig. 1, a system architecture 100 may include a terminal device 101, a network 102, and a server 103. Network 102 is the medium used to provide communication links between terminal devices 101 and server 103. Network 102 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.
A user may use terminal device 101 to interact with server 103 over network 102 to receive or send messages and the like. The terminal apparatus 101 may be hardware or software. When the terminal apparatus 101 is hardware, it may be various electronic apparatuses. Including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like. When the terminal apparatus 101 is software, it can be installed in the above-described electronic apparatus. It may be implemented as multiple pieces of software or software modules, or as a single piece of software or software module. And is not particularly limited herein.
The server 103 may provide various services. For example, the server 103 may analyze and perform processing such as analysis on data such as a subject relationship binary group and a text acquired from the terminal apparatus 101, and generate a processing result (for example, a subject relationship object ternary group).
The server 103 may be hardware or software. When the server 103 is hardware, it may be implemented as a distributed server cluster composed of a plurality of servers, or may be implemented as a single server. When the server 103 is software, it may be implemented as multiple pieces of software or software modules (e.g., to provide distributed services), or as a single piece of software or software module. And is not particularly limited herein.
It should be noted that the method for generating information provided in the embodiment of the present application is generally performed by the server 103, and accordingly, the apparatus for generating information is generally disposed in the server 103.
It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
With continued reference to FIG. 2, a flow 200 of one embodiment of a method for generating information in accordance with the present application is shown. The method for generating information comprises the following steps:
In this embodiment, the executing agent (e.g., server 103 shown in fig. 1) of the method for generating information may obtain the agent relationship bigram and the text. Where a body-relationship doublet may include a body and a relationship, also referred to as an SP doublet. The text may be information describing a subject-relationship binary, and the content thereof includes not only the subject and the relationship but also an attribute value of the relationship, that is, an object.
In this embodiment, the execution body may segment the text into a sequence of text words. Generally, the execution body may segment the text into word granularity by using a word segmentation technique to obtain a text word sequence.
And 203, inputting the body relationship binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence.
In this embodiment, the execution agent may input the agent relationship binary group and the text word sequence to a pre-trained slot filling model to obtain a labeling result of the text word sequence. The slot filling model can be used for labeling the object in the text word sequence, so that the labeling result at least labels the object in the text word sequence.
Here, the slot filling model may extract an object corresponding to the subject relationship binary group from the text by using a slot filling technique given the text and the subject relationship binary group. The slot filling model is added with the positions of the main body and the relation and the semantic similarity of the relation, and is a sequence labeling model. And inputting the main body relation binary group and the text word sequence by the slot filling model, and outputting a labeling result of each word in the text word sequence. And identifying the words belonging to the objects corresponding to the subject relation binary group in the text word sequence according to the labeling result.
In some optional implementations of this embodiment, the slot filling model may label the text word sequence in a biees sequence labeling manner. Where B, begin, represents the starting position of the object labels of the multiple words. I.e., inside, denotes the middle part of the object notation of a plurality of words. O is outside, which means a moiety that is not a guest. E, end, indicates the ending position of the object labels of the plurality of words. S, single, represents the object of a single word.
And step 204, generating a subject relation object triple based on the subject relation binary group and the labeling result.
In this embodiment, the execution subject may generate the subject-relationship object triple based on the subject-relationship binary group and the tagging result of the text word sequence. The subject-relationship-object triple may include a subject, a relationship, and an object of a text. Specifically, the execution subject may determine the object according to different marks in the labeling result of the text word sequence, and then combine the object into a subject-relationship binary group to generate a subject-relationship object triple. For example, the execution subject may extract a word labeled B, I, E as an object from the labeling result of the text word sequence, or extract a word labeled S as an object.
Generally, the method provided by the embodiment is used for generating a large number of subject-relationship object triples, and can be used for constructing the knowledge graph, improving the connectivity of the knowledge graph and efficiently improving the knowledge richness of the knowledge graph. In addition, from the application perspective, the subject relationship object triple can directly meet the search requirement of the user on the knowledge class. When a user searches the subject relation binary group, the related information of the corresponding object can be directly provided, and the retrieval and browsing efficiency of the user is effectively improved. When the user searches the subject, the related information of the corresponding object can be provided, and the content of the information pushed to the user is greatly enriched.
According to the method and the device for generating the information, the principal relation binary group and the text are firstly obtained; then cutting the text into text word sequences; then, inputting the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence; and finally, generating a subject relation object triple based on the subject relation binary group and the labeling result. The object is identified based on the slot filling model, the sum structure of the main body and the relation is reserved, and the object identification accuracy is improved.
With further reference to FIG. 3, a flow 300 of yet another embodiment of a method for generating information in accordance with the present application is illustrated. The slot filling model in the method for generating information may comprise an input layer, a positioning layer, an embedding layer, an encoding layer, a decoding layer and an output layer. Wherein, the coding layer may include a first Bidirectional Long Short Term Memory network (Bi-LSTM). The decoding layer may include a location attention module, a relationship attention module, and a second bidirectional long-short term memory network. Specifically, the method for generating information includes the steps of:
In the present embodiment, the specific operations of steps 301 and 302 have been described in detail in step 201 and 202 in the embodiment shown in fig. 2, and are not described herein again.
And step 303, inputting the main body relationship binary group and the text word sequence into an input layer to obtain a word sequence characteristic and a distance characteristic.
In this embodiment, an executing agent (e.g., the server 103 shown in fig. 1) of the method for generating information may input the agent relationship binary group and the text word sequence to the input layer, and obtain a word sequence feature and a distance feature. Wherein the input layer can be used for extracting the characteristics of the main body relationship binary group and the text word sequence. Word sequence characteristics may include, but are not limited to, at least one of: a sequence of text words, a sequence of parts-of-speech of a sequence of text words, a sequence of named entity identifications of a sequence of text words and a sequence of related words of a relationship, and the like. The distance features may include, but are not limited to, at least one of: the distance of a word in a sequence of text words to the subject, the distance of a word in a sequence of text words to a relationship, and so on.
And step 304, inputting the distance characteristics into a positioning layer to obtain position information.
In this embodiment, the execution subject may input the distance feature to the positioning layer to obtain the position information. The positioning layer is connected with the output layer and can position the position information of the words in the text word sequence based on the characteristics of the distance from the words in the text word sequence to the main body and the distance from the words in the text word sequence to the relation.
In this embodiment, the execution body may input the word sequence feature and the position information to the embedding layer to obtain a word sequence vector and a position. The embedded layer is connected with the output layer and the positioning layer respectively, so that word sequence characteristics such as a text word sequence, a part-of-speech sequence of the text word sequence, a named entity recognition sequence of the text word sequence, a relation word sequence of a relation and the like can be vectorized, and position information of words in the text word sequence can be vectorized.
It should be noted that the vector matrix for vectorizing the word sequence features in the embedding layer is different from the vector matrix for vectorizing the position features.
In this embodiment, the execution body may input the word sequence vector to the coding layer to obtain a coding vector. The coding layer is connected with the embedding layer and can code the word sequence vectors. Since the coding layer includes the first bidirectional long short term memory network, the coding layer can encode the word sequence vector using the first bidirectional long short term memory network.
And 307, splicing the position vector and the coding vector and inputting the spliced position vector and coding vector to a position attention module to obtain position information of a word distance main body and relation in the text word sequence.
In this embodiment, the execution main body may first splice the position vector and the encoding vector, and then input the spliced vector to the position attention module to obtain position information of the word distance main body and the relationship in the text word sequence.
Here, the execution body may input the position vector and the encoded vector to a decoding layer, resulting in a decoded vector. The coding layer introduces a long short term memory network coder with attention mechanism in order to add more input information. That is, the decoding layer is composed of a position attention module, a relation attention module and a second bidirectional long-short term memory network. The position attention module is connected with the embedding layer and the coding layer respectively, and can add position attention of a main body and a relation in the slot filling model, namely adding position information of a word in a text word sequence from the main body and the relation as different weights into the slot filling model. The relation attention module is connected with the coding layer and can be used for calculating the importance degree of the relation between each word in the input text word sequence and the main body relation binary group, so that more information is transmitted to the words related to the relation in the decoding process. And the second bidirectional long-short term memory network is respectively connected with the position attention module, the relation attention module and the coding layer, inputs the coding vector obtained by the coding layer, the position information of the word distance main body and the relation in the text word sequence obtained by the position attention module and the semantic similarity of the word and the relation in the text word sequence obtained by the relation attention module, and outputs the decoding vector of the word in the text word sequence.
In this embodiment, the execution body may input the long and short term memory network coding and the coding vector of the relationship to the relationship attention module to obtain semantic similarity between words and relationships in the text word sequence. Specifically, the executing agent may first perform long-short term memory network coding on the relationship in the two-tuple of the relationship of the executing agent to obtain long-short term memory network coding of the relationship, and then input the long-short term memory network coding of the relationship and the obtained coding vector of the coding layer to the relationship attention module together to obtain semantic similarity between the word in the text word sequence and the relationship.
In this embodiment, the execution main body may input the encoding vector, the position information of the word distance main body and the relation in the text word sequence, and the semantic similarity between the word and the relation in the text word sequence to the second bidirectional long-short term memory network, so as to obtain the decoding vector.
In this embodiment, the execution body may input the decoding vector to the output layer to obtain the labeling result. Wherein, the output layer is connected with the second bidirectional long-term and short-term memory network in the decoding layer.
In some optional implementation manners of this embodiment, the execution main body may perform multi-classification on the decoding vectors of the words in the text word sequence through an activation function, so as to obtain a probability that a word in the text word sequence belongs to each of multiple categories; and labeling the text word sequence based on the category corresponding to the maximum probability of the words in the text word sequence to generate a labeling result. Where multi-classification is the calculation of the probability that a word belongs to each of a plurality of classes. The activation function may be, for example, Softmax, which may perform multi-classification on the decoding vector of each word in the text word sequence, characterize relative probabilities between different classes, that is, score the probabilities of several labels, i.e., biees, respectively, and then take the label with the highest probability, thereby completing labeling of each word in the sequence.
And 311, generating a subject relation object triple based on the subject relation binary group and the labeling result.
In this embodiment, the specific operation of step 311 has been described in detail in step 204 in the embodiment shown in fig. 2, and is not described herein again.
For ease of understanding, fig. 4 shows a schematic view of the structure of the slot filling model. As shown in fig. 4, the slot filling model may include an input layer, a positioning layer, an embedding layer, an encoding layer, a decoding layer, and an output layer. Wherein the encoding layer may comprise a first Bi-LSTM and the decoding layer may comprise a location attention module, a relationship attention module, and a second Bi-LSTM. If it is desired to extract the showing time of the tv series "XX", the main body "XX" and the relation "showing time" may be combined into a relation binary group < XX, showing time >, and the text "XX" describing the relation binary group < XX, showing time > is obtained, and the series is shown on the upper line of 8 month and 10 days 2015. The text "XX, which is drawn on day 10/8/2015" may be cut into a text word sequence "XX, which is drawn on day 10/8/2015". The main body relationship binary < XX, mapping time > and the text word sequence "XX" which is shown on line "8/10/2015 on day" are input into the slot filling model, and the corresponding labeling result "O, B, I, E, O" is obtained. It can be seen that the words "2015 year", "8 months" and "10 days" in the text word sequence are labeled as objects of the subject relationship binary group < XX, mapping time >, so that the generated subject relationship object triple is < XX, mapping time, 2015 year 8 months and 10 days >.
As can be seen from fig. 3, the flow 300 of the method for generating information in the present embodiment highlights the structure of the slot filling model compared to the corresponding embodiment of fig. 2. Therefore, according to the scheme described in this embodiment, the position attention module and the relationship attention module are added to the slot filling model, so that the positions of the subject and the relationship, the semantic similarity of the relationship, and other information are increased, and the object recognition accuracy is further improved.
With further reference to fig. 5, as an implementation of the methods shown in the above-mentioned figures, the present application provides an embodiment of an apparatus for generating information, which corresponds to the method embodiment shown in fig. 2, and which is particularly applicable to various electronic devices.
As shown in fig. 5, the apparatus 500 for generating information of the present embodiment may include: an acquisition unit 501, a segmentation unit 502, a labeling unit 503 and a generation unit 504. The obtaining unit 501 is configured to obtain a subject relationship binary group and a text, where the subject relationship binary group includes a subject and a relationship; a segmentation unit 502 configured to segment the text into a sequence of text words; a labeling unit 503 configured to input the subject relationship binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, wherein the slot filling model is used for labeling an object in the text word sequence; the generating unit 504 is configured to generate a subject-relationship-object triple based on the subject-relationship binary and the labeling result, where the subject-relationship-object triple includes a subject, a relationship, and an object of the text.
In the present embodiment, in the apparatus 500 for generating information: the specific processing of the obtaining unit 501, the segmenting unit 502, the labeling unit 503 and the generating unit 504 and the technical effects thereof can refer to the related descriptions of step 201 and step 204 in the corresponding embodiment of fig. 2, which are not repeated herein.
In some optional implementations of this embodiment, the slot filling model includes an input layer, a positioning layer, an embedding layer, an encoding layer, a decoding layer, and an output layer.
In some optional implementations of this embodiment, the labeling unit 503 includes: an input subunit (not shown in the figure) configured to input the principal relation binary group and the text word sequence into the input layer, obtaining a word sequence characteristic and a distance characteristic; a positioning subunit (not shown in the figure) configured to input the distance feature into a positioning layer, resulting in position information; an embedding subunit (not shown in the figure) configured to input the word sequence characteristics and the position information into the embedding layer, resulting in a word sequence vector and a position vector; an encoding subunit (not shown in the figure) configured to input the word sequence vector to an encoding layer, resulting in an encoded vector; a decoding sub-unit (not shown in the figure) configured to input the position vector and the encoded vector to a decoding layer, resulting in a decoded vector; and an output subunit (not shown in the figure) configured to input the decoding vector to the output layer, and obtain the labeling result.
In some optional implementations of this embodiment, the encoding layer includes a first bidirectional long-short term memory network, and the decoding layer includes a location attention module, a relationship attention module, and a second bidirectional long-short term memory network.
In some optional implementations of this embodiment, the encoding subunit is further configured to: splicing the position vector and the coding vector and inputting the spliced position vector and the coding vector into a position attention module to obtain position information of a word distance main body and a relation in a text word sequence; inputting the long and short term memory network coding and coding vector of the relation to a relation attention module to obtain semantic similarity between words and relations in the text word sequence; and inputting the coding vector, the position information of the word distance main body and the relation in the text word sequence and the semantic similarity of the words and the relation in the text word sequence into a second bidirectional long-short term memory network to obtain a decoding vector.
In some optional implementations of this embodiment, the output subunit is further configured to: performing multi-classification on decoding vectors of words in the text word sequence through an activation function to obtain the probability that the words in the text word sequence belong to each of multiple categories, wherein the multi-classification is to calculate the probability that the words belong to each of the multiple categories; and labeling the text word sequence based on the category corresponding to the maximum probability of the words in the text word sequence to generate a labeling result.
In some optional implementations of this embodiment, the word sequence feature includes at least one of: the method comprises the following steps of (1) a text word sequence, a part of speech sequence of the text word sequence, a named entity recognition sequence of the text word sequence and a relation word sequence of a relation, wherein distance characteristics comprise at least one of the following items: the distance from a word in the sequence of text words to the subject, and the distance from a word in the sequence of text words to the relationship.
In some optional implementation manners of this embodiment, the slot filling model adopts a biees sequence tagging manner to tag the text word sequence.
Referring now to FIG. 6, a block diagram of a computer system 600 suitable for use in implementing an electronic device (e.g., server 103 shown in FIG. 1) of an embodiment of the present application is shown. The electronic device shown in fig. 6 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present application.
As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU)601 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data necessary for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.
The following components are connected to the I/O interface 605: an input portion 606 including a keyboard, a mouse, and the like; an output portion 607 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The driver 610 is also connected to the I/O interface 605 as needed. A removable medium 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 610 as necessary, so that a computer program read out therefrom is mounted in the storage section 608 as necessary.
In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 609, and/or installed from the removable medium 611. The computer program performs the above-described functions defined in the method of the present application when executed by a Central Processing Unit (CPU) 601.
It should be noted that the computer readable medium described herein can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, a computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or electronic device. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present application may be implemented by software or hardware. The described units may also be provided in a processor, and may be described as: a processor includes an obtaining unit, a segmentation unit, a labeling unit, and a generation unit. Where the names of these units do not constitute a limitation on the unit itself in this case, for example, the acquisition unit may also be described as a "unit that acquires a subject relationship binary and text".
As another aspect, the present application also provides a computer-readable medium, which may be contained in the electronic device described in the above embodiments; or may exist separately without being assembled into the electronic device. The computer readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring a main body relation binary group and a text, wherein the main body relation binary group comprises a main body and a relation; segmenting the text into a sequence of text words; inputting the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, wherein the slot filling model is used for labeling objects in the text word sequence; and generating a subject relation object triple based on the subject relation binary group and the labeling result, wherein the subject relation object triple comprises a subject, a relation and an object of the text.
The above description is only a preferred embodiment of the application and is illustrative of the principles of the technology employed. It will be appreciated by those skilled in the art that the scope of the invention herein disclosed is not limited to the particular combination of features described above, but also encompasses other arrangements formed by any combination of the above features or their equivalents without departing from the spirit of the invention. For example, the above features may be replaced with (but not limited to) features having similar functions disclosed in the present application.
Claims (18)
1. A method for generating information, comprising:
acquiring a main body relation binary group and a text, wherein the main body relation binary group comprises a main body and a relation;
segmenting the text into a sequence of text words;
inputting the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, wherein the slot filling model is used for labeling objects in the text word sequence;
and generating a subject relation object triple based on the subject relation binary group and the labeling result, wherein the subject relation object triple comprises the subject, the relation and the object of the text.
2. The method of claim 1, wherein the slot filling model comprises an input layer, a positioning layer, an embedding layer, an encoding layer, a decoding layer, and an output layer.
3. The method of claim 2, wherein the inputting the principal relation duplets and the text word sequences into a pre-trained slot filling model to obtain labeling results of the text word sequences comprises:
inputting the main body relation binary group and the text word sequence into the input layer to obtain word sequence characteristics and distance characteristics;
inputting the distance features into the positioning layer to obtain position information;
inputting the word sequence characteristics and the position information into the embedding layer to obtain a word sequence vector and a position vector;
inputting the word sequence vector into the coding layer to obtain a coding vector;
inputting the position vector and the coding vector into the decoding layer to obtain a decoding vector;
and inputting the decoding vector to the output layer to obtain the labeling result.
4. The method of claim 3, wherein the encoding layer comprises a first bidirectional long-short term memory network, and the decoding layer comprises a location attention module, a relational attention module, and a second bidirectional long-short term memory network.
5. The method of claim 4, wherein said inputting the position vector and the encoded vector to the decoding layer resulting in a decoded vector comprises:
splicing the position vector and the coding vector is input to the position attention module to obtain position information of the distance between the words in the text word sequence and the main body and the relation;
inputting the long-short term memory network coding and the coding vector of the relation into the relation attention module to obtain semantic similarity between the words in the text word sequence and the relation;
and inputting the coding vector, the position information of the distance between the words in the text word sequence and the main body and the relation and the semantic similarity between the words in the text word sequence and the relation to the second bidirectional long-short term memory network to obtain the decoding vector.
6. The method of claim 3, wherein said inputting the decoded vector to the output layer resulting in the annotated result comprises:
performing multi-classification on the decoding vectors of the words in the text word sequence through an activation function to obtain the probability that the words in the text word sequence belong to each of multiple categories, wherein the multi-classification is to calculate the probability that the words belong to each of the multiple categories;
and labeling the text word sequence based on the category corresponding to the maximum probability of the words in the text word sequence to generate a labeling result.
7. The method according to one of claims 3 to 6, wherein the word sequence features comprise at least one of: the text word sequence, the part of speech sequence of the text word sequence, the named entity recognition sequence of the text word sequence, and the relation word sequence of the relation, wherein the distance characteristics include at least one of: a distance from a word in the sequence of text words to the subject, a distance from a word in the sequence of text words to the relationship.
8. The method according to one of claims 1 to 6, wherein the slot filling model labels the sequence of text words with a BIOES sequence labeling.
9. An apparatus for generating information, comprising:
an acquisition unit configured to acquire a subject relationship binary group and a text, wherein the subject relationship binary group includes a subject and a relationship;
a segmentation unit configured to segment the text into a sequence of text words;
the labeling unit is configured to input the subject relation binary group and the text word sequence into a pre-trained slot filling model to obtain a labeling result of the text word sequence, wherein the slot filling model is used for labeling objects in the text word sequence;
and the generating unit is configured to generate a subject relation object triple based on the subject relation binary group and the labeling result, wherein the subject relation object triple comprises a subject, a relation and an object of the text.
10. The apparatus of claim 9, wherein the slot filling model comprises an input layer, a positioning layer, an embedding layer, an encoding layer, a decoding layer, and an output layer.
11. The apparatus of claim 10, wherein the labeling unit comprises:
an input subunit, configured to input the principal relation binary group and the text word sequence to the input layer, to obtain a word sequence feature and a distance feature;
a positioning subunit configured to input the distance feature to the positioning layer, resulting in position information;
an embedding subunit configured to input the word sequence features and the position information to the embedding layer, resulting in a word sequence vector and a position vector;
an encoding subunit configured to input the word sequence vector to the encoding layer, resulting in an encoded vector;
a decoding subunit configured to input the position vector and the encoded vector to the decoding layer, resulting in a decoded vector;
an output subunit configured to input the decoding vector to the output layer, resulting in the labeling result.
12. The apparatus of claim 11, wherein the encoding layer comprises a first bidirectional long-short term memory network, and the decoding layer comprises a location attention module, a relationship attention module, and a second bidirectional long-short term memory network.
13. The apparatus of claim 12, wherein the encoding subunit is further configured to:
splicing the position vector and the coding vector is input to the position attention module to obtain position information of the distance between the words in the text word sequence and the main body and the relation;
inputting the long-short term memory network coding and the coding vector of the relation into the relation attention module to obtain semantic similarity between the words in the text word sequence and the relation;
and inputting the coding vector, the position information of the distance between the words in the text word sequence and the main body and the relation and the semantic similarity between the words in the text word sequence and the relation to the second bidirectional long-short term memory network to obtain the decoding vector.
14. The apparatus of claim 11, wherein the output subunit is further configured to:
performing multi-classification on the decoding vectors of the words in the text word sequence through an activation function to obtain the probability that the words in the text word sequence belong to each of multiple categories, wherein the multi-classification is to calculate the probability that the words belong to each of the multiple categories;
and labeling the text word sequence based on the category corresponding to the maximum probability of the words in the text word sequence to generate a labeling result.
15. The apparatus according to one of claims 11-14, wherein the word sequence features comprise at least one of: the text word sequence, the part of speech sequence of the text word sequence, the named entity recognition sequence of the text word sequence, and the relation word sequence of the relation, wherein the distance characteristics include at least one of: a distance from a word in the sequence of text words to the subject, a distance from a word in the sequence of text words to the relationship.
16. The apparatus according to one of claims 9 to 14, wherein the slot filling model labels the sequence of text words with a biees sequence labeling.
17. An electronic device, comprising:
one or more processors;
a storage device having one or more programs stored thereon,
when executed by the one or more processors, cause the one or more processors to implement the method of any one of claims 1-8.
18. A computer-readable medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, carries out the method according to any one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010005728.9A CN111241209B (en) | 2020-01-03 | 2020-01-03 | Method and device for generating information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010005728.9A CN111241209B (en) | 2020-01-03 | 2020-01-03 | Method and device for generating information |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111241209A true CN111241209A (en) | 2020-06-05 |
CN111241209B CN111241209B (en) | 2023-07-11 |
Family
ID=70865425
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010005728.9A Active CN111241209B (en) | 2020-01-03 | 2020-01-03 | Method and device for generating information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111241209B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111639500A (en) * | 2020-04-23 | 2020-09-08 | 平安国际智慧城市科技股份有限公司 | Semantic role labeling method and device, computer equipment and storage medium |
CN112560475A (en) * | 2020-11-16 | 2021-03-26 | 和美(深圳)信息技术股份有限公司 | Triple extraction method and system |
CN113743118A (en) * | 2021-07-22 | 2021-12-03 | 武汉工程大学 | Entity relation extraction method in legal document based on fusion relation information coding |
CN114372454A (en) * | 2020-10-14 | 2022-04-19 | 腾讯科技(深圳)有限公司 | Text information extraction method, model training method, device and storage medium |
CN117407492A (en) * | 2023-12-14 | 2024-01-16 | 广东海洋大学 | Keyword sequence generation method, system and equipment based on knowledge graph |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778186A (en) * | 2014-01-15 | 2015-07-15 | 阿里巴巴集团控股有限公司 | Method and system for hanging commodity object to standard product unit (SPU) |
US20180060306A1 (en) * | 2016-08-25 | 2018-03-01 | Abbyy Infopoisk Llc | Extracting facts from natural language texts |
CN109325201A (en) * | 2018-08-15 | 2019-02-12 | 北京百度网讯科技有限公司 | Generation method, device, equipment and the storage medium of entity relationship data |
CN109408812A (en) * | 2018-09-30 | 2019-03-01 | 北京工业大学 | A method of the sequence labelling joint based on attention mechanism extracts entity relationship |
CN110147437A (en) * | 2019-05-23 | 2019-08-20 | 北京金山数字娱乐科技有限公司 | A kind of searching method and device of knowledge based map |
CN110275962A (en) * | 2019-06-25 | 2019-09-24 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
CN110275963A (en) * | 2019-06-25 | 2019-09-24 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
US20190294648A1 (en) * | 2018-03-23 | 2019-09-26 | Baidu Online Network Technology (Beijing) Co., Ltd. | Artificial intelligence-based triple checking method and apparatus, device and storage medium |
CN110472235A (en) * | 2019-07-22 | 2019-11-19 | 北京航天云路有限公司 | A kind of end-to-end entity relationship joint abstracting method towards Chinese text |
-
2020
- 2020-01-03 CN CN202010005728.9A patent/CN111241209B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778186A (en) * | 2014-01-15 | 2015-07-15 | 阿里巴巴集团控股有限公司 | Method and system for hanging commodity object to standard product unit (SPU) |
US20180060306A1 (en) * | 2016-08-25 | 2018-03-01 | Abbyy Infopoisk Llc | Extracting facts from natural language texts |
US20190294648A1 (en) * | 2018-03-23 | 2019-09-26 | Baidu Online Network Technology (Beijing) Co., Ltd. | Artificial intelligence-based triple checking method and apparatus, device and storage medium |
CN109325201A (en) * | 2018-08-15 | 2019-02-12 | 北京百度网讯科技有限公司 | Generation method, device, equipment and the storage medium of entity relationship data |
CN109408812A (en) * | 2018-09-30 | 2019-03-01 | 北京工业大学 | A method of the sequence labelling joint based on attention mechanism extracts entity relationship |
CN110147437A (en) * | 2019-05-23 | 2019-08-20 | 北京金山数字娱乐科技有限公司 | A kind of searching method and device of knowledge based map |
CN110275962A (en) * | 2019-06-25 | 2019-09-24 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
CN110275963A (en) * | 2019-06-25 | 2019-09-24 | 北京百度网讯科技有限公司 | Method and apparatus for output information |
CN110472235A (en) * | 2019-07-22 | 2019-11-19 | 北京航天云路有限公司 | A kind of end-to-end entity relationship joint abstracting method towards Chinese text |
Non-Patent Citations (3)
Title |
---|
SAURABH SRIVASTAVA ET AL.: "Hierarchical Capsule Based Neural Network Architecture for Sequence Labeling", 《2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)》 * |
曹明宇 等: "基于神经网络的药物实体与关系联合抽取", 《计算机研究与发展》, vol. 56, no. 7 * |
马黎: "基于最大二元组和综合特征的文本分类框架", 《西北师范大学学报(自然科学版)》, no. 5 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111639500A (en) * | 2020-04-23 | 2020-09-08 | 平安国际智慧城市科技股份有限公司 | Semantic role labeling method and device, computer equipment and storage medium |
WO2021212681A1 (en) * | 2020-04-23 | 2021-10-28 | 平安国际智慧城市科技股份有限公司 | Semantic role annotation method and apparatus, and computer device and storage medium |
CN114372454A (en) * | 2020-10-14 | 2022-04-19 | 腾讯科技(深圳)有限公司 | Text information extraction method, model training method, device and storage medium |
CN112560475A (en) * | 2020-11-16 | 2021-03-26 | 和美(深圳)信息技术股份有限公司 | Triple extraction method and system |
CN112560475B (en) * | 2020-11-16 | 2023-05-12 | 和美(深圳)信息技术股份有限公司 | Triplet extraction method and system |
CN113743118A (en) * | 2021-07-22 | 2021-12-03 | 武汉工程大学 | Entity relation extraction method in legal document based on fusion relation information coding |
CN117407492A (en) * | 2023-12-14 | 2024-01-16 | 广东海洋大学 | Keyword sequence generation method, system and equipment based on knowledge graph |
CN117407492B (en) * | 2023-12-14 | 2024-02-23 | 广东海洋大学 | Keyword sequence generation method, system and equipment based on knowledge graph |
Also Published As
Publication number | Publication date |
---|---|
CN111241209B (en) | 2023-07-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107679039B (en) | Method and device for determining statement intention | |
CN107491547B (en) | Search method and device based on artificial intelligence | |
CN111241209B (en) | Method and device for generating information | |
CN111274815A (en) | Method and device for mining entity attention points in text | |
CN111709240A (en) | Entity relationship extraction method, device, equipment and storage medium thereof | |
CN112860919B (en) | Data labeling method, device, equipment and storage medium based on generation model | |
CN110807311B (en) | Method and device for generating information | |
US11036996B2 (en) | Method and apparatus for determining (raw) video materials for news | |
CN113947095B (en) | Multilingual text translation method, multilingual text translation device, computer equipment and storage medium | |
CN113158656B (en) | Ironic content recognition method, ironic content recognition device, electronic device, and storage medium | |
CN116661805B (en) | Code representation generation method and device, storage medium and electronic equipment | |
CN114970553B (en) | Information analysis method and device based on large-scale unmarked corpus and electronic equipment | |
CN114218940B (en) | Text information processing and model training method, device, equipment and storage medium | |
CN115798661A (en) | Knowledge mining method and device in clinical medicine field | |
US20230367972A1 (en) | Method and apparatus for processing model data, electronic device, and computer readable medium | |
CN111027333A (en) | Chapter translation method and device | |
CN112599211B (en) | Medical entity relationship extraction method and device | |
CN117874234A (en) | Text classification method and device based on semantics, computer equipment and storage medium | |
CN115859121B (en) | Text processing model training method and device | |
CN113722584A (en) | Task pushing method and device and storage medium | |
CN113657104A (en) | Text extraction method and device, computer equipment and storage medium | |
CN113111169A (en) | Deep learning model-based alarm receiving and processing text address information extraction method and device | |
CN117131152B (en) | Information storage method, apparatus, electronic device, and computer readable medium | |
CN113255292B (en) | End-to-end text generation method based on pre-training model and related equipment | |
CN116383655B (en) | Sample generation method, model training method, text processing method and device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |