Elamur Research⌕
☰
home / papers / 2006 / Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution

Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution

Summary

This paper tests whether semantic knowledge can improve a machine-learned coreference resolver. Coreference systems at the time mostly used shallow cues such as string match, distance and grammatical form. The authors re-implemented the Soon et al. (2001) pairwise classifier as a Maximum Entropy model (MALLET with a Gaussian prior). They then added three kinds of semantic features. The first is similarity scores computed over the WordNet taxonomy. The second is relatedness scores based on the Wikipedia category graph. The third is predicate–argument information from semantic role labeling (SRL). Noun phrases were extracted automatically rather than taken from gold annotations. The system was tested on the ACE 2003 training corpus, split into training, development and test parts. Adding the features together and then pruning them with feature selection raised the MUC F-measure on every section. The biggest gains came from higher recall and better resolution of pronouns and common nouns. The paper also shows that a collaboratively built encyclopedia can be nearly as useful as a curated lexical resource, which made Wikipedia a practical knowledge source for NLP.

Key points

  • Data: ACE 2003 training data, Newswire (NWIRE) and Broadcast News (BNEWS), split 60/20/20 by document and also evaluated as a MERGED set. The system was first prototyped on MUC-6 and MUC-7.
  • Results (MUC F1, baseline → all features): BNEWS 60.6 → 69.5, NWIRE 69.0 → 71.7, MERGED 67.3 → 70.7.
  • By expression type (MERGED): common-noun accuracy rose from 20.4 to 29.9 and pronoun accuracy from 34.7 to 38.9. The SRL features mainly helped pronouns, while WordNet and Wikipedia mainly helped common nouns.
  • Feature selection: on BNEWS, a Wikipedia Wu–Palmer similarity feature added the most (+4.3 F1 over a 58.4 baseline), followed by SRL and Wikipedia path features. The full feature set was highly redundant, so pruning it was necessary.
  • Resources: an English Wikipedia dump from February 2006, WordNet similarity measures (Pedersen et al.), LingPipe NER and an automatic NP chunker.

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: Linguistics & languages

Topics: Coreference resolution · Semantic role labeling

Cited by

89 papers of our library cite it (of the 140673 whose bibliographies we read); 37 of them have a page here, 52 not yet.

Cite

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

@inproceedings{ponzetto2006exploiting,
  title = {{Exploiting Semantic Role Labeling, WordNet and Wikipedia for Coreference Resolution}},
  author = {Ponzetto, Simone Paolo and Strube, Michael},
  booktitle = {Proceedings of the Human Language Technology Conference of the NAACL, Main Conference},
  year = {2006},
  url = {https://aclanthology.org/N06-1025/}
}

References

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

  1. Banerjee, S. & T. Pedersen (2003). Extended gloss overlap as a measure of semantic relatedness. In Proc. of IJCAI-03, pp. 805–810. find
  2. Berger, A., S. A. Della Pietra & V. J. Della Pietra (1996). A maximum entropy approach to natural language processing. Computational Linguistics, 22(1):39–71. find our card
  3. Charniak, E. (1973). Jack and Janet in search of a theory of knowledge. In Advance Papers from the Third International Joint Conference on Artificial Intelligence, Stanford, Cal., pp. 337–343. find
  4. Chinchor, N. (2001). Message Understanding Conference (MUC) 7. LDC2001T02, Philadelphia, Penn: Linguistic Data Consortium. find
  5. Chinchor, N. & B. Sundheim (2003). Message Understanding Conference (MUC) 6. LDC2003T13, Philadelphia, Penn: Linguistic Data Consortium. find
  6. Gildea, D. & D. Jurafsky (2002). Automatic labeling of semantic roles. Computational Linguistics, 28(3):245–288. find our card
  7. Giménez, J. & L. Màrquez (2004). SVMTool: A general POS tagger generator based on support vector machines. In Proc. of LREC ’04, pp. 43–46. find our card
  8. Harabagiu, S. M., R. C. Bunescu & S. J. Maiorano (2001). Text and knowledge mining for coreference resolution. In Proc. of NAACL-01, pp. 55–62. find
  9. Ji, H., D. Westbrook & R. Grishman (2005). Using semantic relations to refine coreference decisions. In Proc. HLT-EMNLP ’05, pp. 17–24. find our card
  10. Jiang, J. J. & D. W. Conrath (1997). Semantic similarity based on corpus statistics and lexical taxonomy. In Proceedings of the 10th International Conference on Research in Computational Linguistics (ROCLING). find
  11. Kehler, A., D. Appelt, L. Taylor & A. Simma (2004). The (non)utility of predicate-argument frequencies for pronoun interpretation. In Proc. of HLT-NAACL-04, pp. 289–296. find
  12. Kohavi, R. & G. H. John (1997). Wrappers for feature subset selection. Artificial Intelligence Journal, 97(1-2):273–324. find
  13. Kudoh, T. & Y. Matsumoto (2000). Use of Support Vector Machines for chunk identification. In Proc. of CoNLL-00, pp. 142–144. find
  14. Leacock, C. & M. Chodorow (1998). Combining local context and WordNet similarity for word sense identification. In C. Fellbaum (Ed.), WordNet. An Electronic Lexical Database, Chp. 11, pp. 265–283. Cambridge, Mass.: MIT Press. find
  15. Lin, D. (1998). An information-theoretic definition of similarity. In Proceedings of the 15th International Conference on Machine Learning, pp. 296–304. find
  16. Luo, X., A. Ittycheriah, H. Jing, N. Kambhatla & S. Roukos (2004). A mention-synchronous coreference resolution algorithm based on the Bell Tree. In Proc. of ACL-04, pp. 136–143. find our card
  17. Markert, K. & M. Nissim (2005). Comparing knowledge sources for nominal anaphora resolution. Computational Linguistics, 31(3):367–401. find our card
  18. McCallum, A. K. (2002). MALLET: A Machine Learning for Language Toolkit. find
  19. Mitchell, A., S. Strassel, M. Przybocki, J. Davis, G. Doddington, R. Grishman, A. Meyers, A. Brunstain, L. Ferro & B. Sundheim (2003). TIDES Extraction (ACE) 2003 Multilingual Training Data. LDC2004T09, Philadelphia, Penn.: Linguistic Data Consortium. find
  20. Ng, V. & C. Cardie (2002). Improving machine learning approaches to coreference resolution. In Proc. of ACL-02, pp. 104–111. find our card
  21. Palmer, M., D. Gildea & P. Kingsbury (2005). The proposition bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–105. find our card
  22. Pedersen, T., S. Patwardhan & J. Michelizzi (2004). Word-Net::Similarity – Measuring the relatedness of concepts. In Companion Volume of the Proceedings of the Human Technology Conference of the North American Chapter of the Association for Computational Linguistics, pp. 267–270. find
  23. Pradhan, S., W. Ward, K. Hacioglu, J. H. Martin & D. Jurafsky (2004). Shallow semantic parsing using Support Vector Machines. In Proc. of HLT-NAACL-04, pp. 233–240. find
  24. Rada, R., H. Mili, E. Bicknell & M. Blettner (1989). Development and application of a metric to semantic nets. IEEE Transactions on Systems, Man and Cybernetics, 19(1):17– 30. find
  25. Resnik, P. (1995). Using information content to evaluate semantic similarity in a taxonomy. In Proc. of IJCAI-95, Vol. 1, pp. 448–453. find our card
  26. Seco, N., T. Veale & J. Hayes (2004). An intrinsic information content metric for semantic similarity in WordNet. In Proc. of ECAI-04, pp. 1089–1090. find
  27. Soon, W. M., H. T. Ng & D. C. Y. Lim (2001). A machine learning approach to coreference resolution of noun phrases. Computational Linguistics, 27(4):521–544. find our card
  28. Strube, M. & S. P. Ponzetto (2006). WikiRelate! Computing semantic relatedness using Wikipedia. In Proc. of AAAI-06. find
  29. Vieira, R. & M. Poesio (2000). An empirically-based system for processing definite descriptions. Computational Linguistics, 26(4):539–593. find
  30. Vilain, M., J. Burger, J. Aberdeen, D. Connolly & L. Hirschman (1995). A model-theoretic coreference scoring scheme. In Proceedings of the 6th Message Understanding Conference (MUC-6), pp. 45–52. find our card
  31. Wu, Z. & M. Palmer (1994). Verb semantics and lexical selection. In Proc. of ACL-94, pp. 133–138. find
  32. Yang, X., J. Su & C. L. Tan (2005). Improving pronoun resolution using statistics-based semantic compatibility information. In Proc. of ACL-05, pp. 165–172. find our card
  33. Yang, X., G. Zhou, J. Su & C. L. Tan (2003). Coreference resolution using competition learning approach. In Proc. of ACL-03, pp. 176–183. find our card

↑ back to top