Natural Language Understanding Wiki
Advertisement

TODO:  Semantic role labeling and coreference resolution

TODO:

☀From Rahman & Ng (2012)[1]: "We employ narrative chains to heuristically predict the antecedent for the target pronoun, and encode the prediction as a feature. [...] we extract all the narrative chains containing both elements in the pair from Chambers and Jurafsky’s output."

From Khashabi & Roth (2015)[2] propose "Predicate schemas" and use them to solve Winnograd-style and regular coreference resolution tasks.

Algorithm Surface-

form

Discourse Syntactic

Structure

One-way

Selectional Preference

Event

Chain

Top F1 Source

Code

Notes
Haghighi and Klein (2010)[1] generative + log-linear?? Y Y Y N N 67.0 on ACE2004-Stoyanov

68.1 on ACE2005-Stoyanov

71.6 on ACE2005-Rahman

N[note 1]
Haghighi and Klein (2009)[2] Y N
Reconcile[3][4] Mention-pair Y Y[note 2] Y utah.edu
Neural Association Models N Y N Evaluated on Winnograd but not standard CR datasets
Rahman and Ng (2011)[5] role pairs predicate pairs N Evaluated on ACE and OntoNotes
Yang et al. (2005)[6] simple co-occurence statistics N
CherryPicker[7][8] Cluster-ranking Y Y Y N N utdallas.edu
BART Y Y Y N N bart-coref.org
Berkeley CR Mention-synchronous Y Y Y N N berkeley.edu
cort[9] Mention-ranking, latent structure Y Y Y N N github
Illinois CR[10] Mention-pair Y Y N N N cogcomp.org
Stanford sieve Sieve
Peng & Roth (2016)[11] (based on Illinois CR) Y Y Y N N frame-chains, frame-and-argument-chains 71.79 on ACE, 63.46 on CoNLL12 See Peng and Roth (2016)

TODO:

Notes[]

  1. "Software release" is mentioned in footnote 11 but links don't contain the code anymore (as of October 2017).
  2. SameParagraph, SameSentence, SentNum, ParNum

References[]

  1. Haghighi, A., & Klein, D. (2010). Coreference resolution in a modular, entity-centered model. Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the ACL, (June), 385–393. http://doi.org/10.3115/1608810.1608821
  2. Haghighi, A., & Klein, D. (2009). Simple Coreference Resolution with Rich Syntactic and Semantic Features. EMNLP 2009, 1152–1161.
  3. Stoyanov, V., Cardie, C., Gilbert, N., Riloff, E., Buttler, D., & Hysom, D. (2010). Reconcile : A Coreference Resolution Research Platform.
  4. Stoyanov, V., Cardie, C., Gilbert, N., Riloff, E., Buttler, D., & Hysom, D. (2010). Coreference resolution with reconcile. In Proceedings of the ACL 2010 Conference Short Papers (pp. 156–161).
  5. Rahman, A., & Ng, V. (2011). Coreference Resolution with World Knowledge. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (pp. 814–824).
  6. Yang, X., Su, J., & Tan, C. L. (2005). Improving Pronoun Resolution Using Statistics-based Semantic Compatibility Information. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics (pp. 165–172). Stroudsburg, PA, USA: Association for Computational Linguistics. http://doi.org/10.3115/1219840.1219861
  7. Altaf Rahman and Vincent Ng. Supervised Models for Coreference Resolution. Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pp. 968-977, 2009.
  8. Ng, V., & Cardie, C. (2002). Improving Machine Learning Approaches to Coreference Resolution. ACL 2012, 104–111.
  9. Sebastian Martschat and Michael Strube. 2015. Latent structures for coreference resolution. Transactions of the Association for Computational Linguis- tics, 3:405–418.
  10. Bengtson, E., & Roth, D. (2008). Understanding the value of features for coreference resolution. Proceedings of the Conference on Empirical Methods in Natural Language Processing - EMNLP ’08, 51(October), 294. http://doi.org/10.3115/1613715.1613756
  11. Peng, H., & Roth, D. (2016). Two Discourse Driven Language Models for Semantics. ACL 2016, 290–300.