Elamur Research⌕
☰
home / papers / 2013 / Parsing Models for Identifying Multiword Expressions

Parsing Models for Identifying Multiword Expressions

Paper · 2013 · Spence Green, Marie-Catherine de Marneffe and Christopher D. Manning

Summary

The paper treats the detection of multiword expressions (MWEs) as part of syntactic parsing. Earlier work handled this as a separate step that classifies n-grams using co-occurrence statistics. That approach misses connections between variants such as part of speech and parts of speech, and it suffers from data sparsity in morphologically rich languages. The authors convert the Arabic (ATB) and French (FTB) treebanks so that each MWE appears as a flat constituent with its own label, for example MWN for nominal compounds. Once a sentence is parsed, the MWE spans can be read directly off the tree. They build two supervised parsers. One is a refined PCFG with a new "factored lexicon" that scores words together with morphological feature tags. The other is a tree substitution grammar (TSG), which can store larger tree fragments. Both parsers clearly outperform the n-gram baseline mwetoolkit on MWE identification. The factored lexicon also improves standard parsing accuracy. The work shows that syntactic context helps recover idiomatic word groups of any length.

Key points

  • Representation: each MWE becomes a flat bracketing with a phrasal label such as MWN. Only contiguous MWEs can be represented this way, so discontinuous idioms are outside the scope.
  • TSG results: the TSG model achieves the best Arabic MWE score (81.9% F1) and a competitive French score (71.3% F1). It also learns MWE rules that humans can read, even though its basic parsing accuracy trails the PCFG parsers.
  • Factored lexicon results: with gold morphology, the factored lexicon model leads on French (87.3% F1) and is close behind on Arabic (78.2% F1). It also comes near state-of-the-art parsing accuracy.
  • Baseline: mwetoolkit was re-implemented in Java and trained as an SVM with an RBF kernel. Its features were MLE, Dice, PMI, Student's t-score and the POS sequence of each n-gram.
  • Annotation consistency: a variation-nucleus check compared the treebanks. The FTB has about 1.10 nuclei per tree and a 9.13% token-level error rate, roughly twice the rate of the PTB and ATB (about 4%).

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

🎓Stanford UniversityStanford · United States434 works · 314,419 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.Idioms & multiword expressions · 217 works

Cite

Cite as Spence Green, Marie-Catherine de Marneffe and Christopher D. Manning. 2013. Parsing Models for Identifying Multiword Expressions. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00139

@article{green2013parsing,
  title = {{Parsing Models for Identifying Multiword Expressions}},
  author = {Spence Green, Marie-Catherine {de Marneffe} and Christopher D. Manning},
  journal = {Computational Linguistics},
  year = {2013},
  doi = {10.1162/coli\_a\_00139},
  url = {https://doi.org/10.1162/coli_a_00139}
}

References

91 references, 21 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Abeillé, A. 1988. Parsing French with Tree Adjoining Grammar: some linguistic accounts. In COLING, pages 7–12, Budapest, Hungary. find
  2. Abeillé, A., L. Clément, and A. Kinyon. 2003. Building a treebank for French. In Anne Type 95% Confidence Interval 4.10% 4.00% 9.13% [8.80%, 23.2%] [17.4%, 34.6%] [19.2%, 36.8%] find
  3. Abeillé, editor, Treebanks: building and using parsed corpora. Kluwer, chapter 10. find
  4. Abeillé, A. and Y. Schabes. 1989. Parsing idioms in lexicalized TAGs. In EACL, pages 1–9, Manchester. find
  5. Arun, A. 2004. Statistical parsing of the French treebank. Master’s thesis, University of Edinburgh. find
  6. Arun, A. and F. Keller. 2005. Lexicalization in crosslinguistic probabilistic parsing: The case of French. In ACL, pages 306–313, Ann Arbor, MI. find
  7. Ashraf, A. 2012. Arabic Idioms: A Corpus-Based Study. Routledge. find
  8. Attia, M. 2006. Accommodating multiword expressions in an Arabic LFG grammar. In Advances in Natural Language Processing, volume 4139. Springer, pages 87–98. find
  9. Attia, M., J. Foster, D. Hogan, J. Le Roux, L. Tounsi, and J. van Genabith. 2010a. Handling unknown words in statistical latent-variable parsing models for Arabic, English and French. In First Workshop on Statistical Parsing of Morphologically-Rich Languages (SPMRL), pages 67–75, Los Angeles, CA.
  10. Attia, M., A. Toral, L. Tounsi, P. Pecina, and J. van Genabith. 2010b. Automatic extraction of Arabic multiword expressions. In Workshop on Multiword Expressions: From Theory to Applications, pages 19–27, Beijing.
  11. Baldwin, T. and S. N. Kim. 2010. Multiword expressions. In N. Indurkhya and F. J. Damerau, editors, Handbook of Natural Language Processing. CRC Press, chapter 12, pages 267–293. find
  12. Bansal, M. and D. Klein. 2010. Simple, accurate parsing with an all-fragments grammar. In ACL, pages 1098–1107, Uppsala. find
  13. Bikel, D. M. 2004. Intricacies of Collins’ parsing model. Computational Linguistics, 30(4):479–511.
  14. Bilmes, J. and K. Kirchoff. 2003. Factored language models and generalized parallel backoff. In NAACL, pages 4–6, Edmonton. find
  15. Blunsom, P. and T. Baldwin. 2006. Multilingual deep lexical acquisition for HPSGs via supertagging. In EMNLP, pages 164–171, Sydney. find
  16. Bod, R. 1992. A computation model of language performance: Data-Oriented Parsing. In COLING, pages 855–859, Nantes. find
  17. Cafferkey, C. 2008. Exploiting multi-word units in statistical parsing and generation. Master’s thesis, Dublin City University. find
  18. Candito, M. and B. Crabbé. 2009. Improving generative statistical parsing with semi-supervised word clustering. In IWPT, pages 138–141, Paris. find
  19. Candito, M., B. Crabbé, and P. Denis. 2010. Statistical French dependency parsing: Treebank conversion and first results. In LREC, pages 1840–1847, Valletta.
  20. Candito, M. and D. Seddah. 2010. Parsing word clusters. In First Workshop on Statistical Parsing of Morphologically-Rich Languages (SPMRL), pages 76–84, Los Angeles, CA. find
  21. Carpuat, M. and M. Diab. 2010. Task-based evaluation of multiword expressions: A pilot study in statistical machine translation. In HLT-NAACL, pages 242–245, Los Angeles, CA. find
  22. Chafe, W. L. 1968. Idiomaticity as an anomaly in the Chomskyan paradigm. Foundations of Language, 4(2):109–127. find
  23. Chomsky, N. 1957. Syntactic Structures. Mouton, London. find
  24. Chomsky, N. 1981. Lectures on Government and Binding: The Pisa Lectures. Foris Publications, Holland. find
  25. Chrupala, G., G. Dinu, and J. van Genabith. 2008. Learning morphology with Morfette. In LREC, pages 2362–2367, Marrakech.
  26. Cohn, T., P. Blunsom, and S. Goldwater. 2010. Inducing tree-substitution grammars. JMLR, 11:3053–3096. find
  27. Cohn, T., S. Goldwater, and P. Blunsom. 2009. Inducing compact but accurate tree-substitution grammars. In HLT-NAACL, pages 548–556, Boulder, CO. find
  28. Constant, M., A. Sigogne, and P. Watrin. 2012. Discriminative strategies to integrate multiword expression recognition and parsing. In ACL, pages 204–212, Jeju. find
  29. Constant, M. and I. Tellier. 2012. Evaluating the impact of external lexical resources into a CRF-based multiword segmenter and part-of-speech tagger. In LREC, pages 646–650, Istanbul. find
  30. Crabbé, B. and M. Candito. 2008. Expériences d’analyse syntaxique statistique du français. In TALN, pages 1–10, Avignon. find
  31. Dickinson, M. 2005. Error Detection and Correction in Annotated Corpora. Ph.D. thesis, The Ohio State University. find
  32. Dybro-Johansen, A. 2004. Extraction automatique de grammaires à partir d’un corpus français. Master’s thesis, Université Paris 7. find
  33. Dyer, C., A. Lopez, J. Ganitkevitch, J. Weese, F. Ture, P. Blunsom, H. Setiawan, V. Eidelman, and P. Resnik. 2010. cdec: A decoder, alignment, and learning framework for finite-state and context-free translation models. In ACL System Demonstrations, pages 7–12, Uppsala.
  34. Evert, S. 2008. The MWE 2008 Shared Task: Ranking MWE candidates. In Presentation at 2008 Workshop on Multiword Expressions, Marrakech. find
  35. Fillmore, C. J., P. Kay, and M. C. O’Connor. 1988. Regularity and idiomaticity in grammatical constructions: The case of let alone. Language, 64(3):501–538. find
  36. Finkel, J. R. and C. D. Manning. 2009. Joint parsing and named entity recognition. In HLT-NAACL, pages 326–334, Boulder, CO.
  37. Goldberg, A. 1995. Constructions: A Construction Grammar Approach to Argument Structure. University Of Chicago Press, Chicago. find
  38. Green, S., M-C. de Marneffe, J. Bauer, and C. D. Manning. 2011. Multiword expression identification with Tree Substitution Grammars: A parsing tour de force with French. In EMNLP, pages 725–735, Edinburgh. find
  39. Green, S. and C. D. Manning. 2010. Better Arabic parsing: Baselines, evaluations, and analysis. In COLING, pages 394–402, Beijing.
  40. Gross, M. 1984. Lexicon-Grammar and the syntactic analysis of French. In COLING-ACL, pages 275–282, Stanford, CA. find
  41. Gross, M. 1986. Lexicon-Grammar: The representation of compound words. In COLING, pages 1–6, Bonn. find
  42. Habash, N. and O. Rambow. 2005. Arabic tokenization, part-of-speech tagging and morphological disambiguation in one fell swoop. In ACL, pages 573–580, Ann Arbor, MI.
  43. Hall, M., E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten. 2009. The WEKA data mining software: An update. SIGKDD Explorations Newsletter, 11:10–18. find
  44. Hogan, D., C. Cafferkey, A. Cahill, and J. van Genabith. 2007. Exploiting multi-word units in history-based probabilistic generation. In EMNLP-CoNLL, pages 267–276, Prague. find
  45. Huang, Z. and M. Harper. 2011. Feature-rich log-linear lexical model for latent variable PCFG grammars. In IJCNLP, pages 219–227, Chiang Mai. find
  46. Jackendoff, R. 1997. The Architecture of the Language Faculty. MIT Press, Cambridge, MA. find
  47. Johnson, M. 1998. PCFG models of linguistic tree representations. Computational Linguistics, 24(4):613–632.
  48. Katz, J. J. and P. M. Postal. 1963. Semantic interpretation of idioms and sentences containing them. M.I.T. Research Laboratory of Electronics Quarterly Progress Report, 70:275–282. find
  49. Klein, D. and C. D. Manning. 2003. Accurate unlexicalized parsing. In ACL, pages 423–430, Sapporo.
  50. Koehn, P. and H. Hoang. 2007. Factored translation models. In EMNLP-CoNLL, pages 868–876, Prague.
  51. Korkontzelos, I. and S. Manandhar. 2010. Can recognising multiword expressions improve shallow parsing? In HLT-NAACL, pages 636–644, Los Angeles, CA. find
  52. Kübler, S. 2005. How do treebank annotation schemes influence parsing results? Or how not to compare apples and oranges. In RANLP, pages 79–88, Borovets. find
  53. Kulick, S., A. Bies, and J. Mott. 2011. Using derivation trees for treebank error detection. In ACL, pages 693–698, Portland, OR. find
  54. Kulick, S., R. Gabbard, and M. Marcus. 2006. Parsing the Arabic Treebank: Analysis and improvements. In TLT, pages 31–42, Prague. find
  55. Laporte, E., T. Nakamura, and S. Voyatzi. 2008. A French corpus annotated for multiword expressions with adverbial function. In LREC Linguistic Annotation Workshop, pages 48–51, Marrakech. find
  56. Levy, R. and G. Andrew. 2006. Tregex and Tsurgeon: Tools for querying and manipulating tree data structures. In LREC, pages 2,231–2,234, Genoa. find
  57. Levy, R. and C. D. Manning. 2003. Is it harder to parse Chinese, or the Chinese treebank? In ACL, pages 439–446, Sapporo. find
  58. Liang, P., M. I. Jordan, and D. Klein. 2010. Type-based MCMC. In HLT-NAACL, pages 573–581, Los Angeles, CA. find
  59. Lin, D. 1999. Automatic identification of non-compositional phrases. In ACL, pages 317–324, College Park, MD.
  60. Maamouri, M., A. Bies, T. Buckwalter, and W. Mekki. 2004. The Penn Arabic Treebank: Building a large-scale annotated Arabic corpus. In NEMLAR, pages 1–8, Cairo. find
  61. Maamouri, M., A. Bies, and S. Kulick. 2008. Enhancing the Arabic Treebank: A collaborative effort toward new annotation guidelines. In LREC, pages 3,192–3,196, Marrakech. find
  62. Maamouri, M., A. Bies, and S. Kulick. 2009. Creating a methodology for large-scale correction of treebank annotation: The case of the Arabic Treebank. In MEDAR, pages 138–144, Cairo. find
  63. Marantz, A. 1997. No escape from syntax: Don’t try morphological analysis in the privacy of your own lexicon. In 21st Annual Penn Linguistics Colloquium, pages 1–15, Philadelphia, PA. find
  64. Marcus, M., M. A. Marcinkiewicz, and B. Santorini. 1993. Building a large annotated corpus of English: The Penn Treebank. Computational Linguistics, 19:313–330.
  65. Nivre, J. and J. Nilsson. 2004. Multiword units in syntactic parsing. In Methodologies and Evaluation of Multiword Units in Real-World Applications (MEMURA), pages 1–8, Lisbon. find
  66. O’Donnell, T. J., J. B. Tenenbaum, and N. D. Goodman. 2009. Fragment grammars: Exploring computation and reuse in language. Technical report, MIT Computer Science and Artificial Intelligence Laboratory Technical Report Series, MIT-CSAIL-TR-2009-013. find
  67. O’Grady, W. 1998. The syntax of idioms. Natural Language and Linguistic Theory, 16:279–312. find
  68. Pecina, P. 2010. Lexical association measures and collocation extraction. Language Resources and Evaluation, 44:137–158. find
  69. Petrov, S. 2009. Coarse-to-Fine Natural Language Processing. Ph.D. thesis, University of California-Berkeley. find
  70. Petrov, S., L. Barrett, R. Thibaux, and D. Klein. 2006. Learning accurate, compact, and interpretable tree annotation. In ACL, pages 443–440, Sydney.
  71. Petrov, S. and D. Klein. 2007. Improved inference for unlexicalized parsing. In HLT-NAACL, pages 404–411, Rochester, MN.
  72. Post, M. and D. Gildea. 2009. Bayesian learning of a tree substitution grammar. In ACL-IJCNLP, Short Papers, pages 45–48, Suntec. find
  73. Rambow, O., D. Chiang, M. Diab, N. Habash, R. Hwa, K. Sima’an, V. Lacey, R. Levy, C. Nichols, and S. Shareef. 2005. Parsing Arabic dialects. Technical report. Johns Hopkins University.
  74. Ramisch, C., A. Villavicencio, and C. Boitet. 2010. mwetoolkit: A framework for multiword expression identification. In LREC, pages 662–669, Valletta. find
  75. Rehbein, I. and J. van Genabith. 2007. Treebank annotation schemes and parser evaluation for German. In EMNLP-CoNLL, pages 630–639, Prague. find
  76. Ryding, K. 2005. A Reference Grammar of Modern Standard Arabic. Cambridge University Press. find
  77. Sag, I. A., T. Baldwin, F. Bond, A. Copestake, and D. Flickinger. 2002. Multiword expressions: A pain in the neck for NLP. In CICLing, pages 1–15, Mexico City.
  78. Sampson, G. and A. Babarczy. 2003. A test of the leaf-ancestor metric for parse accuracy. Natural Language Engineering, 9:365–380. find
  79. Scha, R. 1990. Taaltheorie en taaltechnologie: competence en performance. In Q. A. M. de Kort and G. L. J. Leerdam, editors, Computertoepassingen in de Neerlandistiek. Landelijke Vereniging van Neerlandici (LVVNjaarboek), pages 7–22. find
  80. Schluter, N. and J. van Genabith. 2007. Preparing, restructuring, and augmenting a French treebank: Lexicalised parsers or coherent treebanks? In Pacling, pages 1–10, Melbourne. find
  81. Seddah, D. 2010. Exploring the Spinal-STIG model for parsing French. In LREC, pages 1,936–1,943, Valletta. find
  82. Seddah, D., M. Candito, and B. Crabbé. 2009. Cross parser evaluation and tagset variation: a French treebank study. In IWPT, pages 150–161, Paris. find
  83. Seddah, D., G. Chrupała, Ö. Çetinoglu, J. Genabith, and M. Candito. 2010. Lemmatization and lexicalized statistical parsing of morphologically rich languages: The case of French. In First Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL), pages 85–93, Los Angeles, CA. find
  84. Seretan, V. 2011. Syntax-Based Collocation Extraction. Springer. find
  85. Siham Boulaknadel, B. D. and D. Aboutajdine. 2008. A multi-word term extraction program for Arabic language. In LREC, pages 1,485–1,488, Marrakech.
  86. Smadja, F. 1993. Retrieving collocations from text: Xtract. Computational Linguistics, 19:143–177.
  87. Toutanova, K., D. Klein, C. D. Manning, and Y. Singer. 2003. Feature-rich part-of-speech tagging with a cyclic dependency network. In NAACL, pages 173–180, Edmonton.
  88. Vijay-Shanker, K. and D. J. Weir. 1993. The use of shared forests in tree adjoining grammar parsing. In EACL, pages 384–393, Utrecht. find
  89. Watrin, P. and T. Francois. 2011. An n-gram frequency database reference to handle MWE extraction in NLP applications. In Workshop on Multiword Expressions: from Parsing and Generation to the Real World, pages 83–91, Portland, OR. find
  90. Wehrli, E. 2000. Parsing and collocations. In Natural Language Processing–NLP 2000, volume 1835 of Lecture Notes in Computer Science. Springer, pages 272–282. find
  91. West, M. 1995. Hyperparameter estimation in Dirichlet process mixture models. Technical report. Duke University. find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/green-2013-parsing-models-identifying-multiword-expressions/