JP2017199363A - 機械翻訳装置及び機械翻訳のためのコンピュータプログラム - Google Patents
機械翻訳装置及び機械翻訳のためのコンピュータプログラム Download PDFInfo
- Publication number
- JP2017199363A JP2017199363A JP2017077021A JP2017077021A JP2017199363A JP 2017199363 A JP2017199363 A JP 2017199363A JP 2017077021 A JP2017077021 A JP 2017077021A JP 2017077021 A JP2017077021 A JP 2017077021A JP 2017199363 A JP2017199363 A JP 2017199363A
- Authority
- JP
- Japan
- Prior art keywords
- sentence
- translation
- tag
- meta information
- unit
- 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.)
- Pending
Links
- 238000013519 translation Methods 0.000 title claims abstract description 319
- 238000004590 computer program Methods 0.000 title claims description 9
- 238000004458 analytical method Methods 0.000 claims description 77
- 230000006870 function Effects 0.000 claims description 12
- 238000003780 insertion Methods 0.000 claims description 12
- 230000037431 insertion Effects 0.000 claims description 12
- 230000000877 morphologic effect Effects 0.000 claims description 8
- 230000014616 translation Effects 0.000 description 295
- 238000012545 processing Methods 0.000 description 73
- 238000013528 artificial neural network Methods 0.000 description 44
- 238000000034 method Methods 0.000 description 33
- 238000013500 data storage Methods 0.000 description 25
- 230000015654 memory Effects 0.000 description 16
- 230000008569 process Effects 0.000 description 16
- 230000008707 rearrangement Effects 0.000 description 16
- 238000010586 diagram Methods 0.000 description 9
- 238000012550 audit Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 238000000926 separation method Methods 0.000 description 5
- 238000006243 chemical reaction Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 238000013179 statistical model Methods 0.000 description 3
- 241000220225 Malus Species 0.000 description 2
- 235000021016 apples Nutrition 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000006227 byproduct Substances 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Machine Translation (AREA)
Abstract
Description
<s> Web サーバー の サービス は 動作 中 か ? </s>
<s> Is the Web server service is running ? </s>
一方、学習に用いる対訳文として次のような平叙文もあり得る。
<s> Web サーバー の サービス は 動作 中 です 。 </s>
<s> The Web server service is running . </s>
両者の表記上の差はごくわずかである。
<s> の Web サーバー サービス は 動作 中 か ? </s>
<s> Is the Web server service is running ? </s>
<s> の Web サーバー サービス は 動作 中 です 。 </s>
<s> The Web server service is running . </s>
両者の表記上の差はごくわずかである。したがって、こうした対訳データを用いた場合には、フレーズテーブルに関して適切な学習ができない。具体的には、同一の日本語フレーズである「<s> の Web サーバー」というフレーズが、上記した2つの対訳において、一方では「<s> The Web server service is」に対応し、他方では「<s> Is the Web server service」に対応している。このため、このフレーズの範囲内では「<s> の Web サーバー」の訳としていずれを選択したらよいかが決定できない。その結果として、頻度が大きい平叙文の方が常に使われることになり、疑問文の翻訳に失敗する。
以下に説明する各実施の形態は、フレーズの範囲を超えたメタ情報を原文に付与することにより、翻訳時にそのメタ情報を参照して適切な訳し分けをする。メタ情報として、以下の実施の形態では原文に付すタグを用いる。複数種類のタグを準備し、原文の文法タイプにより(第1の実施の形態)、場面又は話者により(第2の実施の形態)、前文脈により(第3の実施の形態)、又は翻訳先の言語により(第4の実施の形態)、異なるタグを原文に付すことにより、適切な訳し分けが行える。学習においても同様のタグ付けをして、フレーズテーブルを含む、翻訳のためのモデルの学習をする必要がある。
第1の実施の形態に係るPBSMTシステムは、PBMSTを行う装置であって、メタ情報としての入力の文法タイプを表すために複数種類のタグを使用する。学習時に、対訳の原文が名詞句であれば、事前並替を行った後の単語列の文頭に開始タグ<NP>を付し、文末に終了タグ</NP>を付してPBSMTの学習を行う。対訳の原文が疑問文であれば、事前並替を行った後の単語列の文頭に開始タグ<SQ>を、文末に終了タグ</SQ>を付して学習を行う。翻訳時には、事前並替を行った入力文に対して、構文解析の結果として得られる文法タイプにしたがったタグを学習時と同様に付してPBSMTを行う。
図6を参照して、この実施の形態に係るPBSMTシステム210は、対訳コーパス220に含まれる対訳データを学習データとして、上記した文法タイプ別のタグ付与を行うことによって、フレーズテーブルを含む翻訳のための統計的モデルの学習を行い、モデル記憶部222に出力するための学習処理部224と、入力文226が与えられると、モデル記憶部222に記憶された翻訳のためのモデルを用いた、PBSMTを行って翻訳文228を出力するための機械翻訳装置230とを含む。
図6及び図7に示す構成を有するPBSMTシステム210は以下のように動作する。PBSMTシステム210の動作フェイズは大きく分けて2つある。第1はモデル記憶部222の学習フェイズ、第2は機械翻訳装置230によるテスト又は翻訳フェイズである。なお、モデルの学習において、学習データからモデルを直接学習する方式もあるし、学習データからモデルを学習した後、モデルに与える素性の重みを最適化する方式もある。いずれの方式に対しても、本実施の形態は有効である。
上記第1の実施の形態に係るPBSMTシステム210によれば、文法タイプによって異なるタグが文頭および文末に付与される。PBSMTでは、フレーズを構成する単語としてこれらタグも考慮される。そのため、同じフレーズであっても文頭にある場合と文中にある場合とを互いに区別できる。また、肯定文と疑問文とがタグにより区別できるようになるため、肯定文から得られるフレーズペアと疑問文から得られるフレーズペアとは、互いに異なるタグを含む。そのため、フレーズテーブルの学習が的確に行える。その結果、翻訳精度が向上する。しかもこの場合、PBSMT装置自体の構成は全く変える必要がない。したがって、簡単な構成により機械翻訳の精度を向上できる。
上記第1の実施の形態では、文法タイプにより異なるタグをメタ情報として原文に付与している。そのために第1の実施の形態では、学習時及び翻訳時に原文に対して行われる構文解析の結果から得られる文法タイプを用いる。しかし本発明はそのような実施の形態には限定されない。例えば、メタ情報を表すタグを予め原文に付与するようにしてもよい。第2の実施の形態はそのような翻訳システムに関する。この実施の形態でも、機械翻訳の方式としてはPBSMTを使用する。
図8に、第2の実施の形態に係るPBSMTシステム320の機能的構成を示す。図8を参照して、PBSMTシステム320は、メタ情報が付された対訳文からなるメタ情報付対訳コーパス240を用いてPBSMTのためのモデルの学習を行い、モデルのパラメータをモデル記憶部342に記憶させる、メタ情報を用いた学習処理部340と、モデル記憶部342に記憶されたモデルパラメータを用い、メタ情報付入力文344に対する機械翻訳を行って翻訳文346を出力する機械翻訳装置348とを含む。
図6に示す第1の実施の形態では、学習時、文法タイプ判定部262により判定された文法タイプを用いて文法タイプ別のタグを単語列に付与している。この第2の実施の形態では、第1の実施の形態とは異なり、学習時、メタ情報分離部370が予めメタ情報が付された対訳文からメタ情報を分離し、タグ付与部374がメタ情報により異なるタグを単語列に付与する。メタ情報として何を用いるかを予め決定しておき、そのメタ情報を学習のための対訳文に付与することで、効率的にメタ情報を用いた機械翻訳のためのモデル学習が行える。
第1の実施の形態では、原文に対する構文解析の結果から判定される文法タイプ情報に基づいてタグを選択している。第2の実施の形態では、予め原文に付与されているメタ情報又は原文を解析することで得られるメタ情報に基づいてタグを選択している。以下に説明する第3の実施の形態では、メタ情報に相当する情報として1つ前の文の文法タイプを文脈情報として記憶しておき、原文にはこの文脈情報に応じて異なるタグを付与する。こうした仕組みにより、文脈に応じて原文を訳し分けることが可能になる。
図9を参照して、この第3の実施の形態に係るPBSMTシステム400は、対訳コーパス220の中の対訳文を用いて機械翻訳のためのモデルの学習を行い、モデルパラメータ等をモデル記憶部410に記憶させるための学習処理部412と、入力文226に対して、モデル記憶部410に記憶されたモデルパラメータ等により構成される翻訳用のモデルを用いてPBSMTを行って翻訳文414を出力する機械翻訳装置416とを含む。
PBSMTシステム400は以下のように動作する。
本実施の形態によれば、翻訳フェイズでは、一文前の原文が否定疑問文か否か等を示す文脈情報が一文前文脈情報記憶部472に記憶されている。この文脈情報に応じたタグを単語列に付与してPBSMT装置288への入力とすることにより、一文前が否定疑問文である場合とそうでない場合等の文脈に応じて適切に訳し分けることが可能になる。
〈構成〉
以下の第4の実施の形態において説明するように、あるタグが付された後、次のタグに遭遇した場合には、前のタグによるメタ情報が影響を及ぼす範囲が終了したものと考えられ、その場合にはメタ情報の終了タグを省略できる。また、翻訳対象の文の末尾に到達した場合に、メタ情報の影響が及ぶ範囲が終わったものと解釈することにより、同様に終了タグを省略できる。
以上に構成を説明した翻訳システム500は以下のように動作する。翻訳システム500の動作には2つのフェイズがある。第1はNNの学習フェイズであり、第2は機械翻訳装置518による翻訳フェイズである。
上記第4の実施の形態に係る翻訳システム500によれば、翻訳先の言語によって異なるタグが文頭に付与される。NNでは、翻訳エンジンであるNNへの入力単語としてこれらタグも考慮される。そのため、こうしたタグを用いて複数の言語の対訳により学習したNNでは、1つのNNで複数の言語間の翻訳が行えるようになる。複数の言語が共通した性質を持つ場合、そのうちのある特定の言語の文を含む対訳の数が少なかったとしても、それ以外で共通した性質を持つ言語の対訳を用いた学習により、そうした特定の言語の翻訳精度も向上することが期待できる。しかもこの場合、NNによる翻訳エンジン自体の構成は全く変える必要がなく、学習時及び翻訳時の前処理として各文の先頭に翻訳先の言語を示すタグを付すだけである。したがって、簡単な構成により機械翻訳の精度を向上できる。
上記実施の形態に係る機械翻訳システム、学習処理部、及び機械翻訳装置は、コンピュータハードウェアと、そのコンピュータハードウェア上で実行されるコンピュータプログラムとにより実現できる。図13はこのコンピュータシステム930の外観を示し、図14はコンピュータシステム930の内部構成を示す。
64、68、84、88、182、192 単語列
66、86、180、190 タグ付与処理
110、220 対訳コーパス
114、258、364、444 モデル学習部
118、226、344、516 入力文
120、230、348、416、518 機械翻訳装置
122、228、346、414、520 翻訳文
140、260、280 形態素解析部
142、372,382 構文解析部
144、264、284 事前並替部
146、274、374、454、474、582、592、604 タグ付与部
148、288 PBSMT装置
184、194 PBSMTによる翻訳
210、320、400 PBSMTシステム
222、342、410 モデル記憶部
240 メタ情報付対訳コーパス
250、540 対訳文読出部
252、360、440 原文処理部
254 翻訳文処理部
256、362、442 学習データ記憶部
262、282 文法タイプ判定部(構文解析部)
266、286 文法タイプ別タグ付与部
224、340、412、512 学習処理部
370、380 メタ情報分離部
384 メタ情報別タグ付与部
450、470 文脈情報記憶部
452、472 一文前文脈情報記憶部
510 マルチリンガル対訳コーパス
514 NNパラメータ記憶部
542 第1文処理部
544 第2文処理部
546 学習データ生成部
548 学習データ記憶部
550 NN学習部
552 NN
602 ターゲット言語記憶部
606 NNによる翻訳エンジン
Claims (8)
- 翻訳に関するメタ情報を特定するためのメタ情報特定手段と、
翻訳の原文の所定位置に、前記メタ情報特定手段により特定されたメタ情報に対応するタグを挿入するためのメタ情報対応タグ挿入手段と、
前記タグが付された前記原文を入力として受ける機械翻訳装置とを含み、
前記メタ情報としては、予め定められた複数種類が規定されており、前記メタ情報対応タグ挿入手段は、前記メタ情報の種類に応じて前記タグを選択する、機械翻訳装置。 - 前記メタ情報対応タグ挿入手段は、前記原文のうちで前記メタ情報を用いた翻訳を行う範囲を特定するために、当該範囲の先頭位置及び終了位置に、前記メタ情報に対応する第1のタグ及び第2のタグをそれぞれ挿入するための範囲特定タグ挿入手段を含む、請求項1に記載の機械翻訳装置。
- 前記メタ情報特定手段は、
前記原文を形態素解析するための形態素解析手段と、
前記形態素解析手段により形態素解析された前記原文の構文解析を行うための構文解析手段と、
前記構文解析手段による前記原文の構文解析結果により得られた、前記原文の文法タイプを示す情報を、当該原文の前記メタ情報として出力するための文法タイプ出力手段とを含む、請求項1又は請求項2に記載の機械翻訳装置。 - 前記原文には、当該原文の翻訳に関する前記メタ情報が付されており、
前記メタ情報特定手段は、前記原文に付されている前記メタ情報を前記原文から分離して前記メタ情報対応タグ挿入手段に与えるためのメタ情報分離手段を含む、請求項1又は請求項2に記載の機械翻訳装置。 - 前記メタ情報は、前記原文の文法タイプ、前記原文が発話される場面に関する場面情報、前記原文を発話する話者に関する話者情報、及び前記原文に先行して前記機械翻訳手段により翻訳された文である先行原文の文法タイプからなるグループから選択される、請求項1、請求項2又は請求項4に記載の機械翻訳装置。
- 前記機械翻訳手段は、句に基づく機械翻訳手段である、請求項1〜請求項5のいずれかに記載の機械翻訳装置。
- 前記メタ情報特定手段は、前記翻訳の原文の翻訳先言語をメタ情報として特定するための手段を含み、
前記メタ情報対応タグ挿入手段は、前記メタ情報により特定される前記翻訳言語を示すタグを前記原文の所定位置に挿入するための手段を含む、請求項1に記載の機械翻訳装置。 - コンピュータを、請求項1〜請求項7のいずれかに記載の機械翻訳装置として機能させる、コンピュータプログラム。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/490,263 US20170308526A1 (en) | 2016-04-21 | 2017-04-18 | Compcuter Implemented machine translation apparatus and machine translation method |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2016085262 | 2016-04-21 | ||
JP2016085262 | 2016-04-21 |
Publications (1)
Publication Number | Publication Date |
---|---|
JP2017199363A true JP2017199363A (ja) | 2017-11-02 |
Family
ID=60238405
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
JP2017077021A Pending JP2017199363A (ja) | 2016-04-21 | 2017-04-07 | 機械翻訳装置及び機械翻訳のためのコンピュータプログラム |
Country Status (1)
Country | Link |
---|---|
JP (1) | JP2017199363A (ja) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018195012A (ja) * | 2017-05-16 | 2018-12-06 | 富士通株式会社 | 学習プログラム、学習方法、学習装置、及び変換パラメータ製造方法 |
WO2019225028A1 (ja) * | 2018-05-25 | 2019-11-28 | パナソニックIpマネジメント株式会社 | 翻訳装置、システム、方法及びプログラム並びに学習方法 |
CN111291575A (zh) * | 2020-02-28 | 2020-06-16 | 北京字节跳动网络技术有限公司 | 文本处理方法、装置、电子设备、及存储介质 |
JP2020160608A (ja) * | 2019-03-25 | 2020-10-01 | 株式会社日立製作所 | 異常検知システム |
KR102406251B1 (ko) * | 2021-11-18 | 2022-06-07 | 염종명 | 언어 현지화에서 번역 완성도를 높이기 위한 자동 번역 및 코딩 방법 |
US11669695B2 (en) | 2019-03-29 | 2023-06-06 | Fujitsu Limited | Translation method, learning method, and non-transitory computer-readable storage medium for storing translation program to translate a named entity based on an attention score using neural network |
KR102640886B1 (ko) * | 2023-08-01 | 2024-02-27 | 주식회사 페이브 | 다국어 웹사이트 콘텐츠를 생성하는 방법 및 전자 장치 |
KR102640887B1 (ko) * | 2023-09-06 | 2024-02-27 | 주식회사 페이브 | 다국어 웹사이트 콘텐츠를 생성하는 방법 및 전자 장치 |
KR102654947B1 (ko) * | 2023-07-17 | 2024-04-05 | 주식회사 페이브 | 다국어 웹사이트 콘텐츠를 생성하는 방법 및 전자 장치 |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07282061A (ja) * | 1994-04-15 | 1995-10-27 | Sharp Corp | 機械翻訳装置 |
JP2000137717A (ja) * | 1998-11-04 | 2000-05-16 | Atr Interpreting Telecommunications Res Lab | 機械翻訳処理装置 |
JP2002041512A (ja) * | 2000-07-26 | 2002-02-08 | Oki Electric Ind Co Ltd | 自然言語処理装置及び方法 |
JP2004199519A (ja) * | 2002-12-19 | 2004-07-15 | Fujitsu Ltd | 機械翻訳方法、機械翻訳装置、および機械翻訳プログラム |
JP2012185622A (ja) * | 2011-03-04 | 2012-09-27 | National Institute Of Information & Communication Technology | 対訳フレーズ学習装置、フレーズベース統計的機械翻訳装置、対訳フレーズ学習方法、および対訳フレーズ生産方法 |
JP2014016475A (ja) * | 2012-07-09 | 2014-01-30 | National Institute Of Information & Communication Technology | 音声処理システム及び端末装置 |
JP2016164707A (ja) * | 2015-03-06 | 2016-09-08 | 国立研究開発法人情報通信研究機構 | 自動翻訳装置及び翻訳用モデル学習装置 |
-
2017
- 2017-04-07 JP JP2017077021A patent/JP2017199363A/ja active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH07282061A (ja) * | 1994-04-15 | 1995-10-27 | Sharp Corp | 機械翻訳装置 |
JP2000137717A (ja) * | 1998-11-04 | 2000-05-16 | Atr Interpreting Telecommunications Res Lab | 機械翻訳処理装置 |
JP2002041512A (ja) * | 2000-07-26 | 2002-02-08 | Oki Electric Ind Co Ltd | 自然言語処理装置及び方法 |
JP2004199519A (ja) * | 2002-12-19 | 2004-07-15 | Fujitsu Ltd | 機械翻訳方法、機械翻訳装置、および機械翻訳プログラム |
JP2012185622A (ja) * | 2011-03-04 | 2012-09-27 | National Institute Of Information & Communication Technology | 対訳フレーズ学習装置、フレーズベース統計的機械翻訳装置、対訳フレーズ学習方法、および対訳フレーズ生産方法 |
JP2014016475A (ja) * | 2012-07-09 | 2014-01-30 | National Institute Of Information & Communication Technology | 音声処理システム及び端末装置 |
JP2016164707A (ja) * | 2015-03-06 | 2016-09-08 | 国立研究開発法人情報通信研究機構 | 自動翻訳装置及び翻訳用モデル学習装置 |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018195012A (ja) * | 2017-05-16 | 2018-12-06 | 富士通株式会社 | 学習プログラム、学習方法、学習装置、及び変換パラメータ製造方法 |
WO2019225028A1 (ja) * | 2018-05-25 | 2019-11-28 | パナソニックIpマネジメント株式会社 | 翻訳装置、システム、方法及びプログラム並びに学習方法 |
JP2020160608A (ja) * | 2019-03-25 | 2020-10-01 | 株式会社日立製作所 | 異常検知システム |
WO2020194809A1 (ja) * | 2019-03-25 | 2020-10-01 | 株式会社日立製作所 | 異常検知システム |
US11669695B2 (en) | 2019-03-29 | 2023-06-06 | Fujitsu Limited | Translation method, learning method, and non-transitory computer-readable storage medium for storing translation program to translate a named entity based on an attention score using neural network |
CN111291575A (zh) * | 2020-02-28 | 2020-06-16 | 北京字节跳动网络技术有限公司 | 文本处理方法、装置、电子设备、及存储介质 |
KR102406251B1 (ko) * | 2021-11-18 | 2022-06-07 | 염종명 | 언어 현지화에서 번역 완성도를 높이기 위한 자동 번역 및 코딩 방법 |
KR102654947B1 (ko) * | 2023-07-17 | 2024-04-05 | 주식회사 페이브 | 다국어 웹사이트 콘텐츠를 생성하는 방법 및 전자 장치 |
KR102640886B1 (ko) * | 2023-08-01 | 2024-02-27 | 주식회사 페이브 | 다국어 웹사이트 콘텐츠를 생성하는 방법 및 전자 장치 |
KR102640887B1 (ko) * | 2023-09-06 | 2024-02-27 | 주식회사 페이브 | 다국어 웹사이트 콘텐츠를 생성하는 방법 및 전자 장치 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP2017199363A (ja) | 機械翻訳装置及び機械翻訳のためのコンピュータプログラム | |
JP4635659B2 (ja) | 質問応答システム、およびデータ検索方法、並びにコンピュータ・プログラム | |
US5895446A (en) | Pattern-based translation method and system | |
KR101762866B1 (ko) | 구문 구조 변환 모델과 어휘 변환 모델을 결합한 기계 번역 장치 및 기계 번역 방법 | |
US20170308526A1 (en) | Compcuter Implemented machine translation apparatus and machine translation method | |
EP1306775A1 (en) | Machine translation | |
EP1351158A1 (en) | Machine translation | |
KR100530154B1 (ko) | 변환방식 기계번역시스템에서 사용되는 변환사전을생성하는 방법 및 장치 | |
EP1349079A1 (en) | Machine translation | |
JP2000353161A (ja) | 自然言語生成における文体制御方法及び装置 | |
JP2005507524A (ja) | 機械翻訳 | |
JP6952967B2 (ja) | 自動翻訳装置 | |
KR20040024619A (ko) | 복수 언어의 대역 텍스트 입력에 의한 제 3 언어 텍스트생성 알고리즘, 장치 및 프로그램 | |
Wax | Automated grammar engineering for verbal morphology | |
Alkım et al. | Machine translation infrastructure for Turkic languages (MT-Turk) | |
JP2005284723A (ja) | 自然言語処理システム及び自然言語処理方法、並びにコンピュータ・プログラム | |
JP4007413B2 (ja) | 自然言語処理システム及び自然言語処理方法、並びにコンピュータ・プログラム | |
JP4114526B2 (ja) | 機械翻訳システム及び機械翻訳方法、並びにコンピュータ・プログラム | |
KR101670995B1 (ko) | 어순 조정 및 형태소 차이에 기반한 통계 기반 기계 번역 시스템 및 그 방법 | |
Alansary et al. | The universal networking language in action in English-Arabic machine translation | |
US11664010B2 (en) | Natural language domain corpus data set creation based on enhanced root utterances | |
KR102143158B1 (ko) | 한국어 구문 분석을 활용한 정보 처리 시스템 | |
US20130080144A1 (en) | Machine translation apparatus, a method and a non-transitory computer readable medium thereof | |
JP2715875B2 (ja) | 多言語要約生成装置 | |
JP2007317140A (ja) | 文一致度分析装置および方法、ならびに言語変換装置および方法 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
A521 | Request for written amendment filed |
Free format text: JAPANESE INTERMEDIATE CODE: A821 Effective date: 20170410 |
|
A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20200311 |
|
A977 | Report on retrieval |
Free format text: JAPANESE INTERMEDIATE CODE: A971007 Effective date: 20210226 |
|
A131 | Notification of reasons for refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A131 Effective date: 20210330 |
|
A02 | Decision of refusal |
Free format text: JAPANESE INTERMEDIATE CODE: A02 Effective date: 20211005 |