Mova0.5 pre-release⌕
☰
home / docs / papers / English / Predicting and Using a Pragmatic Component of Lexical Aspect of Simple Past Verbal Tenses for Improving English-to-French Machine Translation

Predicting and Using a Pragmatic Component of Lexical Aspect of Simple Past Verbal Tenses for Improving English-to-French Machine Translation

What it is about

The paper takes the English simple past and asks whether its boundedness (whether the event is seen as reaching a boundary) helps a statistical machine translation system choose the French tense. Two annotators labelled 435 simple-past verbs as bounded or unbounded, using three tests (compatibility with in or for adverbials, homogeneity, and the progressive entailment test). They agreed on 92% of items, with Cohen's kappa 0.84, and resolved the rest by discussion (kappa 1). Bounded verbs were mostly translated as passé composé or passé simple, and unbounded verbs as imparfait (360 items, 82%). A maximum-entropy classifier predicts boundedness with an accuracy of 0.8857 using manual features, and 0.8224 using only automatically generated features; a random baseline reaches 0.5402. Adding the predicted labels to the translation system gives +0.98 BLEU overall and +1.58 on the sentences with simple-past verbs; a 90% bootstrap interval for the gain is [0.62, 2.85].

Ideas

For Mova

The chapters are 13. Verbs (tense and aspect) and 30. Pragmatics and discourse: overview. The code is en/src/tag.rs for the features, prag/src/frames.rs for the verb reading, and world/src/events.rs for the event types. The measures: the rule accuracy of the three tests against gold, the kappa of a two-pass annotation, and the ablation table. The machine translation part is not Mova's goal; the boundedness labels are the part to borrow.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@misc{loaiciga2016predicting,
  title = {{Predicting and Using a Pragmatic Component of Lexical Aspect of Simple Past Verbal Tenses for Improving English-to-French Machine Translation}},
  author = {Loáiciga, Sharid and Grisot, Cristina},
  year = {2016},
  url = {https://aclanthology.org/2016.lilt-13.3/}
}

References

40 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Bohnet, Bernd, Joakim Nivre, Igor Boguslavsky, Richárd Farkas, Filip Ginter, and Jan Hajič. 2013. Joint morphological and syntactic analysis for richly inflected languages. Transactions of the Association for Computational Linguistics 1:415–428. find
  2. Bojar, Ondřej, Christian Buck, Christian Federmann, Barry Haddow, Philipp Koehn, Johannes Leveling, Christof Monz, Pavel Pecina, Matt Post, Herve Saint-Amand, Radu Soricut, Lucia Specia, and Aleš Tamchyna. 2014. Findings of the 2014 workshop on statistical machine translation. In Proceedings of the Ninth Workshop on Statistical Machine Translation, WMT14, pages 12–58. Baltimore, Maryland: Association for Computational Linguistics. find
  3. Bojar, Ondřej, Rajen Chatterjee, Christian Federmann, Barry Haddow, Matthias Huck, Chris Hokamp, Philipp Koehn, Varvara Logacheva, Christof Monz, Matteo Negri, Matt Post, Carolina Scarton, Lucia Specia, and Marco Turchi. 2015. Findings of the 2015 workshop on statistical machine translation. In Proceedings of the Tenth Workshop on Statistical Machine Translation, WMT15, pages 1–46. Lisbon, Portugal: Association for Computational Linguistics. find
  4. Carletta, Jean. 1996. Assessing agreement on classification tasks: The kappa statistic. Computational Linguistics 22(2):249–254. find
  5. Comrie, Bernard. 1976. Aspect: An Introduction to the Study of Verbal Aspect and Related Problems. Cambridge: Cambridge University Press. find
  6. Comrie, Bernard. 1985. Tense. Cambridge: Cambridge University Press. find
  7. Declerck, Renaat. 1991a. Comprehensive Descriptive Grammar of English. Tokio: Kaitakusha. find
  8. Declerck, Renaat. 1991b. Tense in English: Its structure and use in discourse. London: Routledge. find
  9. Declerck, Renaat. 2006. The Grammar of the English Verb Phrase, vol. 1 of The Grammar of the English Tense System. Berlin: Mouton de Gruyter. find
  10. Depraetere, Ilse. 1995a. The effect of temporal adverbials on (a) telicity and (un) boundednesss. In B. P.-M., V. Bianchi, O. Dahl, and M. Squartini, eds., Temporal reference, aspect and actionality. Turin: Rosenberg and Sel-lier. find
  11. Depraetere, Ilse. 1995b. On the necessity of distinguishing between (un)boundedness and (a)telicity. Linguistics and Philosophy 18(1):1–19. find
  12. Dowty, David. 1979. Word Meaning and Montague Grammar , chap. Word meaning and Montague grammar: The semantics of verbs and times in generative semantics and in Montague’s PTQ. Springer. find
  13. Eisele, Andreas and Yu Chen. 2010. Multiun: A multilingual corpus from united nation documents. In Proceedings of the 7th International Conference on Language Resources and Evaluation, pages 2868–2872. European Language Resources Association (ELRA). find
  14. Gojun, Anita and Alexander Fraser. 2012. Determining the Placement of German Verbs in English-to-German SMT. In Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, EACL, pages 726–735. Avignon, France. find
  15. Gong, Zhengxian, Min Zhang, Chewlim Tan, and Guodong Zhou. 2012a. Classifier-based tense models for SMT. In Proceedings of the 25th International Conference on Computational Linguistics, COLING 2012, pages 411–420. Mumbai, India: The COLING 2012 Organizing Committee. find
  16. Gong, Zhengxian, Min Zhang, Chewlim Tan, and Guodong Zhou. 2012b. N-gram-based tense models for statistical machine translation. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL’12, pages 276–285. Jeju Island, Korea: Association for Computational Linguistics. find
  17. Grisot, Cristina. 2015. Temporal reference: empirical and theoretical perspectives. Converging evidence from English and Romance. Ph.D. thesis, Université de Geneve, Geneva, Switzerland. Manuscript. find
  18. Grisot, Cristina and Bruno Cartoni. 2012. Une description bilingue des temps verbaux: étude contrastive en corpus. Nouveaux cahiers de linguistique française 30:101–117. find
  19. Hardmeier, Christian, Joakim Nivre, and Jörg Tiedemann. 2012. Document-wide decoding for phrase-based statistical machine translation. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 1179–1190. Jeju Island, Korea: Association for Computational Linguistics. find
  20. Hardmeier, Christian, Sara Stymne, Jörg Tiedemann, Aaron Smith, and Joakim Nivre. 2014. Anaphora models and reordering for phrase-based SMT. In Proceedings of the Ninth Workshop on Statistical Machine Translation, pages 122–129. Baltimore, Maryland, USA: Association for Computational Linguistics. find
  21. Heafield, Kenneth. 2011. KenLM: faster and smaller language model queries. In Proceedings of the Sixth Workshop on Statistical Machine Translation, pages 187–197. Edinburgh, Scotland, UK: Association for Computational Linguistics. find
  22. Koehn, Philipp. 2004. Statistical significance tests for machine translation evaluation. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, A meeting of SIGDAT, a Special Interest Group of the ACL, held in conjunction with ACL 2004 , EMNLP 2004, pages 388–395. Barcelona, Spain. find
  23. Koehn, Philipp. 2010. Machine Translation. Cambridge: Cambridge University Press. find
  24. Koehn, Philipp and Hieu Hoang. 2007. Factored translation models. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL, pages 868–876. References / 33 find
  25. Koehn, Philipp, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoli, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Christopher J. Dyer, Ondřej Bojar, Alexandra Constantin, and Evan Herbst. 2007. Moses: Open Source Toolkit for Statistical Machine Translation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, pages 177–180. Prague, Czech Republic: Association for Computational Linguistics. find
  26. Loáiciga, Sharid, Thomas Meyer, and Andrei Popescu-Belis. 2014. English-French verb phrase alignment in Europarl for tense translation modeling. In Proceedings of the 9th International Conference on Language Resources and Evaluation, LREC’14, pages 674–681. Reykjavik, Iceland: European Language Resources Association (ELRA). find
  27. Manning, Christopher and Dan Klein. 2003. Optimization, MaxEnt models, and conditional estimation without magic. In Tutorial at HLT-NAACL and 41st ACL conferences. Edmonton, Canada and Sapporo, Japan. find
  28. Meyer, Thomas. 2014. Discourse-level Features for Statistical Machine Translation. Ph.D. thesis, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland. find
  29. Meyer, Thomas, Cristina Grisot, and Andrei Popescu-Belis. 2013. Detecting narrativity to improve English to French translation of simple past verbs. In Proceedings of the First DiscoMT Workshop at the 51th Annual Meeting of the Association for Computational Linguistics, ACL 2013, pages 33–42. Sofia, Bulgaria. find
  30. Och, Franz Josef. 2003. Minimum error rate training in statistical machine translation. In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1 , ACL ’03, pages 160–167. Stroudsburg, PA: Association for Computational Linguistics. find
  31. Olsen, Mari, David Traum, Carol Van Ess-Dykema, and Amy Weinberg. 2001. Implicit cues for explicit generation: Using telicity as a cue for tense structure in a chinese to english mt system. Tech. Rep. LAMP-TR-070,CS-TR-4248,UMIACS-TR-2001-33, University of Maryland, College Park. find
  32. Papineni, Kishore, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: a method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, ACL’02, pages 311–318. Philadelphia: Association for Computational Linguistics. find our card
  33. Reichenbach, Hans. 1947. Elements of symbolic logic. New York: Mcmillan. find
  34. Schmid, Helmut. 1994. Probabilistic part-of-speech tagging using decision trees. In Proceedings of International Conference on New Methods in Language Processing. Manchester, UK. find
  35. Song, Xingyi, Trevor Cohn, and Lucia Specia. 2013. BLEU deconstructed: Designing a better MT evaluation metric. International Journal of Computational Linguistics and Applications . find
  36. Vendler, Zeno. 1957. Verbs and times. The Philosophical Review 66(2):143– 160. find
  37. Witten, Ian H., Eibe Frank, and Mark A. Hall. 2011. Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann. find
  38. Ye, Yang, Victoria Li Fossum, and Steven Abney. 2006. Latent features in automatic tense translation between chinese and english. In Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing, pages 48–55. Sydney, Australia: Association for Computational Linguistics. find
  39. Ye, Yang, Karl-Michael Schneider, and Steven Abney. 2007. Aspect marker generation for english-to-chinese machine translation. In Proceedings of the Eleventh Machine Translation Summit, MT SUMMIT XI, pages 521–527. Copenhagen, Danmark. find
  40. Zhang, Ying, Stephan Vogel, and Alex Waibel. 2004. Interpreting BLEU/NIST scores: How much improvement do we need to have a better system. In Proceedings of the 4th International Conference on Language Resources and Evaluation, LREC 2004. Lisbon, Portugal: European Language Resources Association (ELRA). find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/loaiciga-2016-predicting-pragmatic-component-lexical-aspect/