MT勉強会/2010

概要

機械翻訳について勉強します。

日時

• 時間:木曜日13:30〜
• 場所:A707

研究テーマ

• 機械翻訳の研究をしています。特に構文情報を用いた機械翻訳の研究に焦点を当てています。
• P.Koehn. Statistical Machine Translation. 2010. (CUP) の輪読もしています。
• NTCIR-9 Patent Translation Task に参加します。

主なメンバー

• 林,雨宮,近藤,水本

予定

日程

11/01/17 15:10- ゼミナール発表練習 近藤 (時間注意)

11/01/13 修士論文進捗報告 近藤

10/12/16 論文 林, 修士論文目次発表練習 雨宮, 近藤

• Zhifei Li, et al. Variational Decoding for Statistical Machine Translation, ACL 2009.

10/12/09 論文 水本, 進捗 近藤

• Chris Brockett, William B. Dolan, and Michael Gamon. Correcting ESL Errors Using Phrasal SMT Techniques. COLING/ACL 2006.

10/12/02 論文 近藤, 進捗 雨宮

• "Soft syntactic constraints for hierarchical phrase-based translation using latent syntactic distributions", Zhongqiang Huang, Martin Cmejrek, Bowen Zhou, EMNLP 2010.

10/11/30 発表練習 林, 近藤

10/11/25 論文 雨宮, 進捗 林

• Bing Xiang et al., Diversify and Combine: Improving Word Alignment for Machine Translation on Low-Resource Languages, ACL. 2010.

10/11/18 NL研のため中止

10/11/11 論文 林, 進捗 水本

• Hui Zhang et. al. Fast Translation Rule Matching for Syntax-based Statistical Machine Translation EMNLP-2009.

10/11/04 論文 水本, 進捗 近藤

• George Foster and Cyril Goutte and Roland Kuhn. Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation. EMNLP-2010.

10/10/29 ゼミナール2発表練習 雨宮

10/10/28 論文 近藤, 進捗 雨宮

• Steve DeNeefe and Kevin Knight. Synchronous Tree Adjoining Machine Translation. EMNLP 2009.

10/10/21 論文 雨宮, 進捗 林

• Chang Liu and Daniel Dahlmeier and Hwee Tou Ng. TESLA: Translation Evaluation of Sentences with Linear-programming-based Analysis. Proc of the Joint Workshop on Statistical Machine Translation and MetricsMATR, pp.354-359, 2010.

10/10/14 論文 林, 進捗 小町 (shared task の調査)

• Zhifei Li and Sanjeev Khudanpur., "Forest Reranking for Machine Translation with the Perceptron Algorithm", 2009.

10/10/07 kickoff meeting

• 今後の予定決め

10/09/09 近藤

• Sudoh et al., "Divide and Translate: Improving Long Distance Reordering in Statistical Machine Translation", WMT 2010.

10/09/02 林

• Haitao Mi, Liang Huang, Qun Liu, "Machine Translation with Lattices and Forests", COLING 2010.

10/07/22 林

• 北 研二，川端 豪，斎藤 博昭, "HMM音韻認識と拡張LR構文解析を用いた連続音声認識". 情報処理学会論文誌. Vol.31. No.3. 1990.

10/07/15 林, 小町

林

• Aria Haghighi and Percy Liang and Taylor Berg-Kirkpatrick and Dan Klein. Learning Bilingual Lexicons from Monolingual Corpora. ACL. 2008.

小町

• Jason Riesa and Daniel Marcu. Hierarchical Search for Word Alignment. ACL. 2010.

10/07/08 林, 近藤

林

• Haitao Mi and Qun Liu. Constituency to Dependency Translation with Forests. ACL. 2010.

近藤 (SMT 本)

• Chapter 4.2.4-

10/07/01 林, 近藤

林

• Liang Huang. K-best Knuth algorithm. unpublished. 2005.

近藤 (SMT 本)

• Chapter 4-4.2.3

10/06/24 小町

• Michel Galley and Christopher D. Manning. Accurate Non-Hierarchical Phrase-Based Translation. NAACL 2010.

10/06/17 ジェシカ

• Maja Popovic and Hermann Ney. Syntax-oriented evaluation measures for machine translation output. WMT-09.
• Preslav Nakov. Improving English-Spanish Statistical Machine Translation: Experiments in Domain Adaptation, Sentence Paraphrasing, Tokenization, and Recasing. WMT-08.

10/06/10 林

• Liang Huang, David Chiang: Forest Rescoring: Faster Decoding with Integrated Language Model, ACL, 2007

10/06/03 松本

• Michel Galley, Jonathan Graehl, Kevin Knight, Daniel Marcu, Steve DeNeefe, Wei Wang, Ignacio Thayer: Scalable Inference and Training of Context-Rich Syntactic Translation Models. ACL 2006

10/05/27

• NL 研でお休み

10/05/20 小町

• Christopher Dyer, Aaron Cordoba, Alex Mont and Jimmy Lin. Fast, Easy, and Cheap: Construction of Statistical Machine Translation Models with MapReduce WMT 2008. (komachi)
• 機械翻訳最新事情 : (上)統計的機械翻訳入門
• (参考) 機械翻訳最新事情 : (下)評価型ワークショップの動向と日本からの貢献

10/05/13 林

• Liang Huang, Kevin Knight and Aravind Joshi. Statistical Syntax-Directed Translation with Extended Domain of Locality. AMTA 2006

関連研究

• The Basics
  • IBM word-alignment models
    • A Statistical Approach to Machine Translation. Brown et al. Computational Linguistics, pp. 79-85. 1990.
    • The mathematics of statistical machine translation: parameter estimation. Brown et al. Computational Linguistics, Volume 19 , Issue 2 , 1993.
  • Phrasal alignment
    • Statistical Phrase-Based Translation. Koehn et al. HLT-NAACL 2003, pp. 48-54.
  • Phrase-based decoding
    • Pharaoh: a Beam Search Decoder for Phrase-based Statistical Machine Translation Models . Koehn. AMTA 2004.
  • N-gram based automatic evaluation
    • BLEU: a Method for Automatic Evaluation of Machine Translation. Papineni et al. ACL 2002, pp. 311-318.
  • Automatic parameter tuning
    • Minimum Error Rate Training in Statistical Machine Translation. Och. ACL 2003, pp. 160-167.
• Alignment
  • Dependency tree based
    • Automatic Learning of Parallel Dependency Treelet Pairs. Ding and Palmer. IJCNLP 2004.
    • Dependency Treelet Translation: Syntactically Informed Phrasal SMT. Quirk et al. ACL 2005.

• Phrase structure tree based
  • Robust Language Pair-Independent Sub-Tree Alignment. Tinsley et al. MT Summit 2007.

• Decoding
  • Phrasal
    • Improvements in Dynamic Programming Beam Search for Phrase-based Statistical Machine Translation. Zens and Ney. IWSLT 2008.
    • Efficient Speech Translation through Confusion Network Decoding. Bertoldi et al. IEEE Transactions on Audio, Speech, and Language Processing, vol. 16, no. 9, pp. 1696-1705, 2008.
  • Hierarchical
    • A Hierarchical Phrase-Based Model for Statistical Machine Translation. Chiang. ACL 2005.
    • NTT Statistical Machine Translation for IWSLT 2006. Watanabe et al. IWSLT 2006.
• Evaluation
  • N-gram based precision with stemming and synonyms
    • METEOR: An Automatic Metric for MT Evaluation with Improved Correlation with Human Judgments. Banerjee and Lavie. MT Summit 2005.

リソース

• コーパス
  • Europarl Parallel Corpus <http://people.csail.mit.edu/koehn/publications/europarl/>
  • Europarl Parallel Corpus (更新版、文レベルのアラインメントあり) <http://www.statmt.org/europarl/>
  • FreeLing (English, Spanish tokenization, POS tagging, NE recognition, dependency parsing) <http://www.lsi.upc.es/~nlp/freeling/>
  • OPUS Corpus (ソフトの説明書、西和データあり) <http://logos.uio.no/opus/>
  • JRC-Acquis (EU法律の訳) <http://langtech.jrc.it/JRC-Acquis.html>
  • 田中コーパス <http://www.csse.monash.edu.au/%7Ejwb/tanakacorpus.html>
• 辞書
  • EDICT (和英英和辞典) <http://www.csse.monash.edu.au/~jwb/j_edict.html>
  • 西和辞典(4500語程度、ダウンロード可能) http://aulex.ohui.net/es-ja/?idioma=ja
  • 西語辞典 http://hp.vector.co.jp/authors/VA016777/link/dict.html#10
  • オンライン西和辞典 http://www.k3.dion.ne.jp/~sugiura/diccSJ.htm
  • 鍋田辞書(データの形式でも入手出来る？) http://www1.udn.ne.jp/~yoiko/nabeta/spain_torikomi.html
    • PDIC用西和辞典データ(シェアウェア) http://www.vector.co.jp/soft/data/writing/se277556.html
    • PDIC用西和辞典旧データ(フリーウェア) http://www1.udn.ne.jp/~yoiko/nabeta/espana08e2_utf8.zip
• SMTの道具
  • アラインメント
    • GIZA++ <http://www.fjoch.com/GIZA++.html>
  • デコーダー
    • Pharaoh (non-open source phrase-based beam0search decoder) <http://www.isi.edu/publications/licensed-sw/pharaoh/>
    • Moses (open source factored phrase-based beam-search decoder) <http://www.statmt.org/moses/>
    • ISI ReWrite Decoder (IBM model 4 greedy decoder) <http://www.isi.edu/licensed-sw/rewrite-decoder/>
    • Cubit (Cube pruning を実装した Python で書かれたデコーダ。Pharaoh 互換) <http://www.cis.upenn.edu/~lhuang3/cubit/>
  • 言語モデル
    • SRILM (n-gram language models) <http://www.speech.sri.com/projects/srilm/>
    • Statistic Language Modeling Toolkit (CMU) <http://mi.eng.cam.ac.uk/%7Eprc14/toolkit.html>
    • IRST LM Toolkit <http://sourceforge.net/projects/irstlm> (開発がオープンな言語モデルのツールキット。Moses からも使える)
    • Palmkit <http://palmkit.sourceforge.net/> (CMU LM Toolkit とコマンドレベルで互換性がある。ライセンスが緩い)
    • mkcls (word class training -- 多くのデコーダーに使用されている) <http://www.fjoch.com/mkcls.html>
  • 評価
    • mteval (Bleu, NIST score calculation) <http://www.nist.gov/speech/tests/mt/resources/scoring.htm>