Elamur Research⌕
☰
home / papers / 2012 / Speculation and Negation: Rules, Rankers, and the Role of Syntax

Speculation and Negation: Rules, Rankers, and the Role of Syntax

Paper · 2012 · Erik Velldal, Lilja Øvrelid, Jonathon Read et al.

Summary

The paper addresses hedging (speculation) and negation in biomedical writing. The task has two parts: spotting the cue words that signal these phenomena, and determining which stretch of the sentence each cue governs. The authors start from their CoNLL-2010 Shared Task entry and first replace its maximum entropy cue detector with a compact linear SVM. The new detector looks only at nearby lexical n-grams and only considers words already attested as cues in training. For scope, they compare two methods: hand-written rules over dependency parses, and an SVM ranker that learns to select the best-matching subtree in HPSG-derived constituent trees. The two methods make different mistakes, so they are merged. The rules act as a fallback when no HPSG parse is available and otherwise supply a feature to the ranker. On the BioScope corpus and the CoNLL-2010 evaluation set, this hybrid gives the strongest published speculation results on that benchmark. With light adaptation, the same pipeline also achieves state-of-the-art negation scope accuracy. The work shows that combining syntax-based rules with learned ranking is both effective and transferable.

Key points

  • Data: BioScope contains 20,924 sentences from abstracts (BSA), full papers (BSP) and clinical reports (BSR). About 18% of the sentences are speculative and about 13% contain negation. The CoNLL-2010 held-out set (BSE) adds 5,003 utterances but has no negation annotation. For negation, the authors run 10-fold cross-validation on BSA and test on BSP and BSR.

  • Preprocessing: The GENIA tagger mis-tokenized roughly one in five training sentences. The authors therefore used a cascaded finite-state tokenizer adapted from the English Resource Grammar, which follows Penn Treebank conventions, and combined GENIA with TnT for PoS tags and lemmas.

  • Caveat on development results: BSA overlaps with the GENIA corpus, so development scores that include the abstracts are likely optimistic.

  • Negation scope results: The full system (cue classifier plus rules plus ranking) is compared with Morante & Daelemans (2009b) using exact-match F1:

    • BSA: 71.05 vs. 65.79
    • BSP: 62.98 vs. 40.72
    • BSR: 89.52 vs. 72.25

    Much of the gain on BSP comes from rules that "back off" from bracketed material such as citations and figure references.

  • Released resources: System outputs for the final speculation and negation configurations are available online, together with the evaluation software.

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

 Institutions

🎓University of OsloOslo · Norway51 works · 4,155 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Syntax & grammar formalisms · 214 works

Cite

Cite as Erik Velldal, Lilja Øvrelid, Jonathon Read and Stephan Oepen. 2012. Speculation and Negation: Rules, Rankers, and the Role of Syntax. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00126

@article{velldal2012speculation,
  title = {{Speculation and Negation: Rules, Rankers, and the Role of Syntax}},
  author = {Erik Velldal, Lilja Øvrelid, Jonathon Read and Stephan Oepen},
  journal = {Computational Linguistics},
  year = {2012},
  doi = {10.1162/coli\_a\_00126},
  url = {https://doi.org/10.1162/coli_a_00126}
}

References

50 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Brants, Thorsten. 2000. TnT. A statistical Part-of-Speech tagger. In Proceedings of the Sixth Conference on Applied Natural Language Processing, pages 224–231, Seattle, WA. — TnT – A Statistical Part-of-Speech Tagger
  2. Butt, Miriam, Helge Dyvik, Tracy Holloway King, Hiroshi Masuichi, and Christian Rohrer. 2002. The Parallel Grammar Project. In Proceedings of the COLING Workshop on Grammar Engineering and Evaluation, pages 1–7, Taipei.
  3. Callmeier, Ulrich. 2002. Preprocessing and encoding techniques in PET. In Stephan Oepen, Daniel Flickinger, Jun’ichi Tsujii, and Hans Uszkoreit, editors, Collaborative Language Engineering. A Case Study in Efficient Grammar-based Processing. CSLI Publications, Stanford, CA, pages 127–143. find
  4. Collier, Nigel, Hyun S. Park, Norihiro Ogata, Yuka Tateishi, Chikashi Nobata, Tomoko Ohta, Tateshi Sekimizu, Hisao Imai, Katsutoshi Ibushi, and Jun I. Tsujii. 1999. The GENIA project: Corpus-based knowledge acquisition and information extraction from genome research papers. In Proceedings of the 9th… find
  5. Councill, Isaac G., Ryan McDonald, and Leonid Velikovich. 2010. What’s great and what’s not: Learning to classify the scope of negation for improved sentiment analysis. In Proceedings of the Workshop on Negation and Speculation in Natural Language Processing, pages 51–59, Uppsala. find
  6. Crouch, Dick, Mary Dalrymple, Ron Kaplan, Tracy King, John Maxwell, and Paula Newman. 2008. XLE documentation. Palo Alto Research Center, Palo Alto, CA. find
  7. Farkas, Richard, Veronika Vincze, Gyorgy Mora, Janos Csirik, and György Szarvas. 2010. find
  8. The CoNLL 2010 Shared Task: Learning to detect hedges and their scope in natural language text. In Proceedings of the 14th Conference on Natural Language Learning, pages 1–12, Uppsala.
  9. Flickinger, Dan. 2002. On building a more efficient grammar by exploiting types. In Stephan Oepen, Dan Flickinger, Jun’ichi Tsujii, and Hans Uszkoreit, editors, Collaborative Language Engineering: A Case Study in Efficient Grammar-based Processing. CSLI Publications, Stanford, CA, pages 1–17.
  10. Gildea, Daniel. 2001. Corpus variation and parser performance. In Proceedings of the 2001 Conference on Empirical Methods in Natural Language Processing, pages 167–202, Pittsburgh, PA.
  11. Joachims, Thorsten. 1999. Making large-scale SVM learning practical. In Bernhard Schölkopf, Christopher J. C. Burges, and Alexander J. Smola, editors, Advances in Kernel Methods: Support Vector Learning. MIT Press, Cambridge, MA, pages 41–56. find
  12. Joachims, Thorsten. 2002. Optimizing search engines using clickthrough data. In Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 133–142, Alberta. find
  13. Johansson, Richard and Pierre Nugues. 2007. Extended constituent-to-dependency conversion for English. In Proceedings of 16th Nordic Conference of Computational Linguistics, pages 105–112, Tartu.
  14. Johnson, Mark, Stuart Geman, Stephen Canon, Zhiyi Chi, and Stefan Riezler. 1999. Estimators for stochastic unification-based grammars. In Proceedings of the 37th Meeting of the Association for Computational Linguistics, pages 535–541, College Park, MD.
  15. Kilicoglu, Halil and Sabine Bergler. 2010. A high-precision approach to detecting hedges and their scopes. In Proceedings of the 14th Conference on Natural Language Learning, pages 70–77, Uppsala.
  16. Light, Marc, Xin Ying Qiu, and Padmini Srinivasan. 2004. The language of bioscience: Facts, speculations, and statements in between. In Proceedings of the HLT-NAACL 2004 Workshop: Biolink 2004, Linking Biological Literature, Ontologies and Databases, pages 17–24, Boston, MA. find
  17. MacKinlay, Andrew, Rebecca Dridan, Dan Flickinger, Stephan Oepen, and Timothy Baldwin. 2011. Treeblazing: Using external treebanks to filter parse forests for parse selection and treebanking. In Proceedings of the 5th International Joint Conference on Natural Language Processing, pages 246–254, Chia… find
  18. Malouf, Robert and Gertjan van Noord. 2004. Wide coverage parsing with stochastic attribute value grammars. In Proceedings of the IJCNLP Workshop Beyond Shallow Analysis, Hainan. find
  19. Marcus, Mitchell P., Beatrice Santorini, and Mary Ann Marcinkiewicz. 1993. Building a large annotated corpus of English. The Penn Treebank. Computational Linguistics, 19(2):313–330.
  20. Martins, Andre F. T., Dipanjan Das, Noah A. Smith, and Eric P. Xing. 2008. Stacking dependency parsers. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 157–166, Waikiki, HI. find
  21. Medlock, Ben and Ted Briscoe. 2007. Weakly supervised learning for hedge classification in scientific literature. In Proceedings of the 45th Meeting of the Association for Computational Linguistics, pages 992–999, Prague.
  22. Moilanen, Karo and Stephen Pulman. 2007. Sentiment composition. In Proceedings of the International Conference on Recent Advances in Natural Language Processing, pages 378–382, Borovets. find
  23. Morante, Roser. 2010. Descriptive analysis of negation cues in biomedical texts. In Proceedings of the 7th International Conference on Language Resources and Evaluation, pages 1429–1436, Valletta. find
  24. Morante, Roser and Walter Daelemans. 2009a. Learning the scope of hedge cues in biomedical texts. In Proceedings of the BioNLP 2009 Workshop, pages 28–36, Boulder, CO.
  25. Morante, Roser and Walter Daelemans. 2009b. A metalearning approach to processing the scope of negation. In Proceedings of the 13th Conference on Natural Language Learning, pages 21–29, Boulder, CO. find
  26. Morante, Roser, Anthony Liekens, and Walter Daelemans. 2008. Learning the scope of negation in biomedical texts. find
  27. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 715–724, Waikiki, HI. find
  28. Morante, Roser, Vincent van Asch, and Walter Daelemans. 2010. Memory-based resolution of in-sentence scope of hedge cues. In Proceedings of the 14th Conference on Natural Language Learning, pages 40–47, Uppsala. find
  29. Nivre, Joakim, Johan Hall, and Jens Nilsson. 2006. MaltParser: A data-driven parser-generator for dependency parsing. In Proceedings of the 5th International Conference on Language Resources and Evaluation, pages 2216–2219, Genoa.
  30. Nivre, Joakim and Ryan McDonald. 2008. Integrating graph-based and transition-based dependency parsers. In Proceedings of the 46th Meeting of the Association for Computational Linguistics, pages 950–958, Columbus, OH.
  31. Øvrelid, Lilja, Jonas Kuhn, and Kathrin Spreyer. 2009. Cross-framework parser stacking for data-driven dependency parsing. TAL special issue on Machine Learning for NLP, 50(3):109–138. find
  32. Øvrelid, Lilja, Erik Velldal, and Stephan Oepen. 2010. Syntactic scope resolution in uncertainty analysis. In Proceedings of the 23rd International Conference on Computational Linguistics, pages 1379–1387, Beijing. find
  33. Petrov, Slav and Dan Klein. 2007. Improved inference for unlexicalized parsing. In Proceedings of Human Language Technologies: The Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 404–411, Rochester, NY.
  34. Pollard, Carl and Ivan A. Sag. 1987. Information-Based Syntax and Semantics. Vol. 1: Fundamentals. CSLI Lecture Notes \# 13. CSLI Press, Stanford, CA. find
  35. Pollard, Carl and Ivan A. Sag. 1994. Head-driven Phrase Structure Grammar. The University of Chicago Press and CSLI Publications, Chicago, IL. find
  36. Rei, Marek and Ted Briscoe. 2010. Combining manual rules and supervised learning for hedge cue and scope detection. In Proceedings of the 14th Conference on Natural Language Learning, pages 56–63, Uppsala.
  37. Riezler, Stefan, Tracy H. King, Ronald M. Kaplan, Richard Crouch, John T. Maxwell, and Mark Johnson. 2002. Parsing the Wall Street Journal using a lexical-functional grammar and discriminative estimation techniques. In Proceedings of the 40th Meeting of the Association for Computational Linguistics,…
  38. Schmid, Helmut. 1994. Probabilistic part-of-speech tagging using decision trees. In International Conference on New Methods in Language Processing, pages 44–49, Manchester. find
  39. Szarvas, György. 2008. Hedge classification in biomedical texts with a weakly supervised selection of keywords. In Proceedings of the 46th Meeting of the Association for Computational Linguistics, pages 281–289, Columbus, OH.
  40. Tang, Buzhou, Xiaolong Wang, Xuan Wang, Bo Yuan, and Shixi Fan. 2010. A cascade method for detecting hedges and their scope in natural language text. In Proceedings of the 14th Conference on Natural Language Learning, pages 13–17, Uppsala.
  41. Toutanova, Kristina, Christopher D. Manning, Dan Flickinger, and Stephan Oepen. 2005. Stochastic HPSG parse disambiguation using the Redwoods corpus. Research on Language and Computation, 3(1):83–105. find
  42. Tsuruoka, Yoshimasa, Yuka Tateishi, Jin-Dong Kim, Tomoko Ohta, John McNaught, Sophia Ananiadou, and Jun’ichi Tsujii. 2005. Developing a robust Part-of-Speech tagger for biomedical text. In P. Bozanis and E. Houstis, editors, Advances in Informatics. Springer, Berlin, pages 382–392. find
  43. Velldal, Erik. 2011. Predicting speculation: A simple disambiguation approach to hedge detection in biomedical literature. Journal of Biomedical Semantics, 2(Suppl 5):S7. find
  44. Velldal, Erik, Lilja Øvrelid, and Stephan Oepen. 2010. Resolving speculation: MaxEnt cue classification and dependency-based scope rules. In Proceedings of the 14th Conference on Natural Language Learning, pages 48–55, Uppsala. find
  45. Vincze, Veronika, György Szarvas, Richárd Farkas, György Móra, and János Csirik. 2008. The BioScope corpus: Biomedical texts annotated for uncertainty, negation and their scopes. BMC Bioinformatics, 9 (Suppl. 11). find
  46. Vlachos, Andreas and Mark Craven. 2010. Detecting speculative language using syntactic dependencies and logistic regression. In Proceedings of the 14th Conference on Natural Language Learning, pages 18–25, Uppsala.
  47. Zhang, Yi, Stephan Oepen, and John Carroll. 2007. Efficiency in unification-based n-best parsing. In Proceedings of the 10th International Conference on Parsing Technologies, pages 48–59, Prague. find
  48. Zhang, Yi and Rui Wang. 2009. Cross-domain dependency parsing using a deep linguistic grammar. In Proceedings of the 47th Meeting of the Association for Computational Linguistics, pages 378–386, Singapore. find
  49. Zhang, Yue and Joakim Nivre. 2011. Transition-based dependency parsing with rich non-local features. In Proceedings of the 49th Meeting of the Association for Computational Linguistics, pages 188–193, Portland, OR. find
  50. Zhu, Qiaoming, Junhui Li, Hongling Wang, and Guodong Zhou. 2010. A unified framework for scope learning via simplified shallow semantic parsing. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 714–724, Cambridge, MA. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/velldal-2012-speculation-negation-rules-rankers-role/