Elamur Research⌕
☰
home / papers / 2010 / Probabilistic Frame-Semantic Parsing

Probabilistic Frame-Semantic Parsing

Summary

The paper treats frame-semantic parsing as a structured prediction task. Given an English sentence, the system must find the words that evoke FrameNet frames, choose the correct frame for each, and mark the text spans that fill that frame's roles. The authors replace the many-classifier SVM pipeline of the strongest SemEval'07 system (J&N'07) with three stages. Targets are found with heuristic rules. Frame identification and argument identification each use one log-linear model with a single weight vector. The frame model has latent variables, so it can disambiguate predicates not listed in the lexicon. Argument identification finds and labels spans jointly, and decoding forbids overlapping arguments of the same predicate, which raises precision. Training uses the small SemEval'07 full-text annotations, preprocessed with MXPOST tags, MST parser dependencies and WordNet lemmatization. FrameNet exemplar sentences enter only as features. The parser beats the previous best results at every stage and on full parsing. It was released as SEMAFOR, a practical tool for semantic analysis.

Key points

  • Resources: FrameNet v. 1.3 (795 frames, 8379 LUs, 7124 roles) and the SemEval'07 data. The training portion has about 43.3K words in 22 documents; the test set has 2.8K words in 3 documents and contains noticeably more annotations and out-of-lexicon items.
  • Training directly on the roughly 139K FrameNet exemplar sentences made results worse, so the exemplars were used only for feature construction.
  • Target identification reached F1 79.21 versus 76.10 for J&N'07. Frame identification on predicted targets reached F1 61.44 versus 57.34 (exact matching) and 68.29 versus 63.97 (partial matching).
  • Full parsing reached F1 46.49 versus 42.01 (exact) and 50.24 versus 45.62 (partial). When given J&N'07's own targets and frames, the argument model alone scored 48.1 versus 45.6 F1.
  • Errors in automatic frame identification reduce full-parse F1 by about 22%. Poor recall, caused by the mismatch between training and test data, remains a known limitation.

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: Semantic role labeling

Cited by

87 papers of our library cite it (of the 140673 whose bibliographies we read); 14 of them have a page here, 73 not yet.

Cite

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

@inproceedings{das2010probabilistic,
  title = {{Probabilistic Frame-Semantic Parsing}},
  author = {Das, Dipanjan and Schneider, Nathan and Chen, Desai and Smith, Noah A.},
  booktitle = {Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics},
  year = {2010},
  url = {https://aclanthology.org/N10-1138/}
}

References

34 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. C. Baker, M. Ellsworth, and K. Erk. 2007. SemEval-2007 Task 19: frame semantic structure extraction. In Proc. of SemEval. find our card
  2. H. C. Boas. 2002. Bilingual FrameNet dictionaries for machine translation. In Proc. of LREC. find our card
  3. L. Bottou. 2004. Stochastic learning. In Advanced Lectures on Machine Learning. Springer-Verlag. find
  4. A. Burchardt, K. Erk, and A. Frank. 2005. A WordNet detour to FrameNet. In B. Fisseni, H.-C. Schmitz, B. Schröder, and P. Wagner, editors, Sprachtech-nologie, mobile Kommunikation und linguistische Re-sourcen, volume 8. Peter Lang. find
  5. A. Burchardt. 2006. Approaching textual entailment with LFG and FrameNet frames. In Proc. of the Second PASCAL RTE Challenge Workshop. find
  6. D. Das, N. Schneider, D. Chen, and N. A. Smith. 2010. SEMAFOR 1.0: A probabilistic frame-semantic parser. Technical Report CMU-LTI-10-001, Carnegie Mellon University. find
  7. K. Erk and S. Padó. 2006. Shalmaneser - a toolchain for shallow semantic parsing. In Proc. of LREC. find
  8. C. Fellbaum, editor. 1998. WordNet: an electronic lexical database. MIT Press, Cambridge, MA. find
  9. C. J. Fillmore, C. R. Johnson, and M. R.L. Petruck. 2003. Background to FrameNet. International Journal of Lexicography, 16(3). find
  10. C. J. Fillmore. 1982. Frame semantics. In Linguistics in the Morning Calm, pages 111–137. Hanshin Publishing Co., Seoul, South Korea. find
  11. M. Fleischman, N. Kwon, and E. Hovy. 2003. Maximum entropy models for FrameNet classification. In Proc. of EMNLP. find our card
  12. P. Fung and B. Chen. 2004. BiFrameNet: bilingual frame semantics resource construction by cross-lingual induction. In Proc. of COLING. find our card
  13. H. Fürstenau and M. Lapata. 2009. Semi-supervised semantic role labeling. In Proc. of EACL. find
  14. D. Gildea and D. Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28(3). find our card
  15. A.-M. Giuglea and A. Moschitti. 2006. Shallow semantic parsing based on FrameNet, VerbNet and PropBank. In Proc. of ECAI 2006. find
  16. R. Johansson and P. Nugues. 2007. LTH: semantic structure extraction using nonprojective dependency trees. In Proc. of SemEval. find
  17. R. Johansson and P. Nugues. 2008. Dependency-based semantic role labeling of PropBank. In Proc. of EMNLP. find our card
  18. P. Kingsbury and M. Palmer. 2002. From TreeBank to PropBank. In Proc. of LREC. find our card
  19. M. P. Marcus, M. A. Marcinkiewicz, and B. Santorini. 1993. Building a large annotated corpus of English: the Penn Treebank. Computational Linguistics, 19(2). find our card
  20. L. Màrquez, X. Carreras, K. C. Litkowski, and S. Stevenson. 2008. Semantic role labeling: an introduction to the special issue. Computational Linguistics, 34(2). find
  21. Y. Matsubayashi, N. Okazaki, and J. Tsujii. 2009. A comparative study on generalization of semantic roles in FrameNet. In Proc. of ACL-IJCNLP. find our card
  22. R. McDonald, K. Crammer, and F. Pereira. 2005. Online large-margin training of dependency parsers. In Proc. of ACL. find our card
  23. A. Moschitti, P. Morărescu, and S. M. Harabagiu. 2003. Open-domain information extraction via automatic semantic labeling. In Proc. of FLAIRS. find
  24. S. Narayanan and S. Harabagiu. 2004. Question answering based on semantic structures. In Proc. of COLING. find
  25. S. Padó and K. Erk. 2005. To cause or not to cause: cross-lingual semantic matching for paraphrase modelling. In Proc. of the Cross-Language Knowledge Induction Workshop. find
  26. S. Padó and M. Lapata. 2005. Cross-linguistic projection of role-semantic information. In Proc. of HLT-EMNLP. find
  27. M. Pennacchiotti, D. De Cao, R. Basili, D. Croce, and M. Roth. 2008. Automatic induction of FrameNet lexical units. In Proc. of EMNLP. find our card
  28. A. Ratnaparkhi. 1996. A maximum entropy model for part-of-speech tagging. In Proc. of EMNLP. find
  29. D. Shen and M. Lapata. 2007. Using semantic roles to improve question answering. In Proc. of EMNLP-CoNLL. find
  30. L. Shi and R. Mihalcea. 2004. An algorithm for open text semantic parsing. In Proc. of Workshop on Robust Methods in Analysis of Natural Language Data. find
  31. L. Shi and R. Mihalcea. 2005. Putting pieces together: combining FrameNet, VerbNet and WordNet for robust semantic parsing. In Computational Linguistics and Intelligent Text Processing: Proc. of CICLing 2005. Springer-Verlag. find
  32. M. Surdeanu, S. Harabagiu, J. Williams, and P. Aarseth. 2003. Using predicate-argument structures for information extraction. In Proc. of ACL. find
  33. C. A. Thompson, R. Levy, and C. D. Manning. 2003. A generative model for semantic role labeling. In Proc. of ECML. find
  34. S. Tonelli and C. Giuliano. 2009. Wikipedia as frame information repository. In Proc. of EMNLP. find

↑ back to top