Elamur Research⌕
☰
home / papers / 2012 / Modality and Negation in SIMT Use of Modality and Negation in Semantically-Informed Syntactic MT

Modality and Negation in SIMT Use of Modality and Negation in Semantically-Informed Syntactic MT

Summary

The paper asks whether semantic knowledge can improve statistical machine translation for a low-resource pair, Urdu–English, when training data is sparse. The work came out of the 8-week SCALE-2009 workshop on Semantically Informed Machine Translation (SIMT). The authors define an annotation scheme for modality and negation (MN). It labels three roles: the trigger word, the target action, and the holder who experiences the modality. They build a semi-automatically derived MN lexicon, which they released publicly, and two automatic taggers, one string-based and one structure-based.

MN tags are attached to English parse trees in the parallel corpus through a method called tree grafting. The tags then flow into syntactically labeled hierarchical translation rules in the Joshua system. The same mechanism also carries named-entity labels from an existing tagger. The combined system clearly beat the plain Hiero baseline, and its scores were the highest yet published for the NIST 2009 Urdu–English evaluation data. This shows that syntax and semantics can be modeled together inside one translation model.

Key points

  • The structure-based MN tagger reaches about 86% precision on a standard LDC data set, with some variation across genres.
  • Modality and negation are merged into single tags such as "NOTAble", which appear as trigger/target pairs (e.g., TrigAble with TargNOTAble).
  • Adding semantic labels through grafting gave roughly +0.5 Bleu over the syntax-only model, although most of the overall gain over Hiero came from syntax.
  • Modality/negation contributed slightly more than named entities, and the two gains were additive.
  • Annotations are produced on the English side and projected onto Urdu during syntactic alignment. The grafting procedure is generic, so the authors propose it for other semantic layers such as relations and temporal information.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Machine translation · Natural language processing

Topics: Part-of-speech tagging · Machine translation

Cited by

12 papers of our library cite it (of the 140673 whose bibliographies we read); 1 of them have a page here, 11 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00099

@article{baker2012modality,
  title = {{Modality and Negation in SIMT Use of Modality and Negation in Semantically-Informed Syntactic MT}},
  author = {Baker, Kathryn and Bloodgood, Michael and Dorr, Bonnie J. and Callison-Burch, Chris and Filardo, Nathaniel W. and Piatko, Christine and Levin, Lori and Miller, Scott},
  journal = {Computational Linguistics},
  year = {2012},
  doi = {10.1162/coli\_a\_00099},
  url = {https://doi.org/10.1162/coli_a_00099}
}

References

48 references, 13 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Baker, Collin F., Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics - Volume 1, ACL ’98, pages 86–90, Stroudsburg, PA. find our card
  2. Baker, Kathryn, Steven Bethard, Michael Bloodgood, Ralf Brown, Chris Callison-Burch, Glen Coppersmith, Bonnie J. Dorr, Nathaniel W. Filardo, Kendall Giles, Ann Irvine, Michael Kayser, Lori Levin, Justin Martineau, James Mayfield, Scott Miller, Aaron Phillips, Andrew Philpot, Christine Piatko, Lane Schwartz, and David Zajic. 2010a. Semantically informed machine translation. Technical Report 002, Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD. find
  3. Baker, Kathryn, Michael Bloodgood, Chris Callison-Burch, Bonnie J. Dorr, Nathaniel W. Filardo, Lori Levin, Scott Miller, and Christine Piatko. 2010b. Semantically-informed machine translation: A tree-grafting approach. In Proceedings of The Ninth Biennial Conference of the Association for Machine Translation in the Americas, Denver, CO. find
  4. Baker, Kathryn, Michael Bloodgood, Mona Diab, Bonnie J. Dorr, Ed Hovy, Lori Levin, Marjorie McShane, Teruko Mitamura, Sergei Nirenburg, Christine Piatko, Owen Rambow, and Gramm Richardson. 2010c. SIMT SCALE 2009—Modality annotation guidelines. Technical Report 004, Human Language Technology Center of Excellence, Johns Hopkins University, Baltimore, MD. find
  5. Baker, Kathryn, Michael Bloodgood, Bonnie J. Dorr, Nathanial W. Filardo, Lori Levin, and Christine Piatko. 2010d. A modality lexicon and its use in automatic tagging. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC), pages 1402–1407, Mediterranean Conference Center, Valletta. find
  6. Bar-Haim, Roy, Ido Dagan, Iddo Greental, and Eyal Shnarch. 2007. Semantic inference at the lexical-syntactic level. In Proceedings of the 22nd National Conference on Artificial intelligence - Volume 1, pages 871–876, Vancouver, British Columbia. find
  7. Bikel, Daniel M., Richard Schwartz, and Ralph M. Weischedel. 1999. An algorithm that learns what’s in a name. Machine Learning, 34(1–3):211–231. ↗
  8. Böhmová, Alena, Silvie Cinková, and Eva Hajičová. 2005. A manual for tectogrammatical layer annotation of the Prague Dependency Treebank [English translation]. Technical Report #30, ÚFAL MFF UK, Prague, Czech Republic. find
  9. Chiang, David. 2005. A hierarchical phrase-based model for statistical machine translation. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL-2005), pages 263–270, Ann Arbor, MI. find our card
  10. Diab, Mona T., Lori Levin, Teruko Mitamura, Owen Rambow, Vinodkumar Prabhakaran, and Weiwei Guo. 2009. Committed belief annotation and tagging. In Proceedings of the Third Linguistic Annotation Workshop, ACL-IJCNLP ’09, pages 68–73, Stroudsburg, PA. find
  11. Farkas, Richárd, Veronika Vincze, György Móra, János Csirik, and György Szarvas. 2010. The CoNLL-2010 shared task: Learning to detect hedges and their scope in natural language text. In Proceedings of the Fourteenth Conference on Computational Natural Language Learning—Shared Task, CoNLL ’10: Shared Task, pages 1–12, Stroudsburg, PA. find our card
  12. Fellbaum, Christiane, editor. 1998. WordNet: An Electronic Lexical Database. MIT Press, Cambridge, MA. find
  13. Hajič, Jan, Eva Hajičová, Petr Pajas, Jarmila Panevová, Petr Sgall, and Barbora Vidová Hladká. 2001. Prague Dependency Treebank 1.0 (Final Production Label), UFAL MFF UK, Prague, Czech Republic. find
  14. Huang, Bryant and Kevin Knight. 2006. Relabeling syntax trees to improve syntax-based machine translation quality. In HLT-NAACL, New York. find
  15. Irvine, Ann, Mike Kayser, Zhifei Li, Wren Thornton, and Chris Callison-Burch. 2010. Integrating output from specialized modules in machine translation: Transliteration in Joshua. Proceedings of the Human Language Technology and North American Chapter of the Association for Computational Linguistics, pages 240–247. The Prague Bulletin of Mathematical Linguistics, 93:107–116. find
  16. Klein, Dan and Christopher D. Manning. 2003. Accurate unlexicalized parsing. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 423–430, Sapporo, Japan. find our card
  17. Koehn, Philipp. 2004. Statistical significance tests for machine translation evaluation. In Proceedings of EMNLP 2004, pages 388–395, Barcelona. find
  18. Koehn, Philipp, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constantin, and Evan Herbst. 2007. Moses: Open source toolkit for statistical machine translation. In Proceedings of the ACL-2007 Demo and Poster Sessions, Prague, Czech Republic, pages 177–180. find
  19. Kratzer, Angelika. 1991. Modality. In Arnim von Stechow and Dieter, editors, Semantics: An International Handbook of Contemporary Research. De Gruyter, Berlin, pages 639–650. find
  20. Larreya, Paul. 2009. Towards a typology of modality in language. In Raphael Salkie, Pierre Busuttil, and Johan van der Auwera, editors, Modality in English: Theory and Description. Mouton de Gruyter, Paris, pages 9–30. ↗
  21. Li, Zhifei, Chris Callison-Burch, Chris Dyer, Sanjeev Khudanpur, Lane Schwartz, Wren Thornton, Jonathan Weese, and Omar Zaidan. 2009. Joshua: An open source toolkit for parsing-based machine translation. In Proceedings of the Fourth Workshop on Statistical Machine Translation, pages 135–139, Athens. find our card
  22. Marcus, Mitchell P., Mary Ann Marcinkiewicz, and Beatrice Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19(2):313–330. ↗ our card
  23. McShane, Marjorie, Sergei Nirenburg, and Ron Zacharski. 2004. Mood and modality: Out of the theory and into the fray. Natural Language Engineering, 19(1):57–89. find
  24. Miller, Scott, Heidi Fox, Lance Ramshaw, and Ralph Weischedel. 1998. SIFT: Statistically-derived information from text. In Seventh Message Understanding Conference (MUC-7), Washington, DC, Miller, Scott, Heidi J. Fox, Lance A. Ramshaw, and Ralph M. Weischedel. 2000. A novel use of statistical parsing to extract information from text. In Proceedings of Applied Natural Language Processing and the North American Association for Computational Linguistics, pages 226–233, Seattle, Washington. find
  25. Murata, Masaki, Kiyotaka Uchimoto, Qing Ma, Toshiyuki Kanamaru, and Hitoshi Isahara. 2005. Analysis of machine translation systems’ errors in tense, aspect, and modality. In Proceedings of the 19th Asia-Pacific Conference on Language, Information and Computing (PACLIC 2005), Taipei, Taiwan. find
  26. Nairn, Rowan, Cleo Condorovdi, and Lauri Karttunen. 2006. Computing relative polarity for textual inference. In Proceedings of the International Workshop on Inference in Computational Semantics (ICoS-5), pages 66–76, Buxton, England. find our card
  27. Palmer, Martha, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31:71–106. ↗ our card
  28. 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-2002), pages 311–318, Philadelphia, PA. find our card
  29. Petrov, Slav and Dan Klein. 2007. Learning and inference for hierarchically split PCFGs. In Proceedings of the 22nd American Association for Artificial Intelligence, pages 1663–1666, Vancouver, British Columbia, Canada. find
  30. Prabhakaran, Vinodkumar, Owen Rambow, and Mona Diab. 2010. Automatic committed belief tagging. In Proceedings of the 23rd International Conference on Computational Linguistics: Posters, COLING ’10, pages 1014–1022, Beijing, China. find
  31. Prasad, Rashmi, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The Penn Discourse TreeBank 2.0. In Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), pages 28–30, Marrakech. find our card
  32. Pustejovsky, James, Marc Verhagen, Roser Saurı́, Jessica Littman, Robert Gaizauskas, Graham Katz, Inderjeet Mani, Robert Knippen, and Andrea Setzer. 2006. TimeBank 1.2. Linguistic Data Consortium, Philadelphia, PA. ↗
  33. Richman, Alexander and Patrick Schone. 2008. Mining wiki resources for multilingual named entity recognition. In Proceedings of ACL-08: HLT, pages 1–9, Columbus, OH. find
  34. Rubin, Victoria L. 2007. Stating with certainty or stating with doubt: Intercoder reliability results for manual annotation of epistemically modalized statements. In Proceedings of the Human Language Technology and North American Chapter of the Association for Computational Linguistics (Short Papers), pages 141–144, Rochester, NY. find
  35. Saurı́, Roser and James Pustejovsky. 2009. FactBank: A corpus annotated with event factuality. Language Resources and Evaluation, 43(3):227–268. find
  36. Saurı́, Roser, Marc Verhagen, and James Pustejovsky. 2006. Annotating and recognizing event modality in text. In Proceedings of the 19th International Florida Artificial Intelligence Research Society Conference, pages 333–339, Melbourne Beach, FL. find
  37. Sigurd, Bengt and Barbara Gawrónska. 1994. Modals as a problem for MT. In Proceedings of the 15th International Conference on Computational Linguistics (COLING) - Volume 1, pages 120–124, Kyoto, Japan. find
  38. Steedman, Mark. 1999. Alternating quantifier scope in CCG. In Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics (ACL), College Park, MD. find
  39. Szarvas, György, Veronika Vincze, Richárd Farkas, and János Csirik. 2008. The BioScope corpus: Annotation for negation, uncertainty and their scope in biomedical texts. In Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing, pages 38–45, Stroudsburg, PA. find our card
  40. van der Auwera, Johan and Andreas Ammann. 2005. Overlap between situational and epistemic modal marking. In Martin Haspelmath, Matthew S. Dryer, David Gil, and Bernard Comrie, editors, World Atlas of Language Structures. Oxford University Press, New York, chapter 76, pages 310–313. find
  41. Venugopal, Ashish and Andreas Zollmann. 2009. Grammar based statistical MT on Hadoop: An end-to-end toolkit for large scale PSCFG based MT. Prague Bulletin of Mathematical Linguistics, 91:67–78. ↗
  42. Venugopal, Ashish, Andreas Zollmann, and Stephan Vogel. 2007. An efficient two-pass approach to synchronous-CFG driven statistical MT. In Proceedings of the Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT/NAACL-2007), pages 500–507, Rochester, NY. ↗
  43. von Fintel, Kai and Sabine Iatridou. 2006. How to say ought in foreign: The composition of weak necessity modals. In Proceedings of the 6th Workshop on Formal Linguistics, Florianopolis, Brazil, August 2006. find
  44. Wang, Wei, Jonathan May, Kevin Knight, and Daniel Marcu. 2010. Re-structuring, re-labeling, and re-aligning for syntax-based machine translation. Computational Linguistics, 36(2):247–277. ↗
  45. Webber, Bonnie, Aravid Joshi, Matthew Stone, and Alistair Knott. 2003. Anaphora and discourse structure. Computational Linguistics, 29:545–587. ↗ our card
  46. Wiebe, Janyce, Theresa Wilson, and Claire Cardie. 2005. Annotating expressions of opinions and emotions in language. Language Resources and Evaluation, 39(2–3):165–210. ↗
  47. Wilson, Theresa, Janyce Wiebe, and Paul Hoffman. 2009. Recognizing contextual polarity: An exploration of features for phrase-level sentiment analysis. Computational Linguistics, 35:399–433. ↗
  48. Zollmann, Andreas and Ashish Venugopal. 2006. Syntax augmented machine translation via chart parsing. In Proceedings on the Workshop on Statistical Machine Translation, pages 138–141, New York City. ↗ our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/baker-2012-modality-negation-simt-use-modality/