Elamur Research⌕
☰
home / papers / 2015 / Context-aware Frame-Semantic Role Labeling

Context-aware Frame-Semantic Role Labeling

Summary

FrameNet-style semantic role labeling usually assigns roles one sentence at a time and learns from a small annotated dataset. Yet the correct role often depends on the surrounding discourse. For example, "Greece" in a delivery event could be a destination (GOAL) or a political actor (RECIPIENT).

Roth and Lapata start from the PropBank/NomBank-oriented SRL pipeline of mate-tools and adapt it to FrameNet. They switch to frame-specific roles, add FrameNet XML input/output, and reuse SEMAFOR's features and preprocessing. The pipeline keeps separate argument identification and labeling steps plus a global reranker. On top of this baseline (Framat), they add three groups of context features:

  • discourse-level cues from coreference chains, such as entity newness and previously assigned roles;
  • sentence-level features describing the whole frame structure;
  • distributional word vectors adapted to each document's content.

The extended model, Framat+context, raises precision by more than 2 percentage points. It reaches state-of-the-art F1 compared with systems built on publicly available tools. The study shows that discourse context, long recognized in frame-semantic theory, brings measurable gains when labeled data is scarce.

Key points

  • Data: FrameNet 1.5 full-text annotations (23,087 frame instances). The resource defines 1,019 frames, 8,886 frame elements and 11,829 frame-evoking elements.
  • Baseline: mate-tools logistic-regression pipeline combined with SEMAFOR features and preprocessing. Hermann et al. (2014) and Täckström et al. (2015) report higher scores, but they depend on proprietary, non-public tools.
  • Main result: discourse-aware features give a gain of over +2.0 points in precision and state-of-the-art F1.
  • Error analysis:
    • For the ambiguous fillers party, power, program and view, precision improves from 86% to 93%.
    • Document-specific vectors reduce false TIME labels, with gains of 14% in precision and 9% in recall.
  • Code is released as "mateplus" at github.com/microth/mateplus. The paper appeared in TACL, vol. 3, 2015, under CC-BY 4.0.

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: Discourse analysis · Semantic role labeling

Cited by

26 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 22 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00150

@article{roth2015context,
  title = {{Context-aware Frame-Semantic Role Labeling}},
  author = {Roth, Michael and Lapata, Mirella},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2015},
  doi = {10.1162/tacl\_a\_00150},
  url = {https://doi.org/10.1162/tacl_a_00150}
}

References

40 references, 6 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Apoorv Agarwal, Sriramkumar Balasubramanian, Anup Kotalwar, Jiehan Zheng, and Owen Rambow. 2014. Frame semantic tree kernels for social network extraction from text. In Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, pages 211–219, Gothenb… find our card
  2. Anders Björkelund, Bernd Bohnet, Love Hafdell, and Pierre Nugues. 2010. A high-performance syntactic and semantic dependency parser. In Coling 2010: Demonstration Volume, pages 33–36, Beijing, China. find
  3. Wanxiang Che, Ting Liu, and Yongqiang Li. 2010. Improving semantic role labeling with word sense. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 246– 249, Los Angeles, California, 1–6 June 2010. find
  4. Bob Coyne, Alex Klapheke, Masoud Rouhizadeh, Richard Sproat, and Daniel Bauer. 2012. Annotation tools and knowledge representation for a text-to-scene system. In Proceedings of 24th International Conference on Computational Linguistics, pages 679–694, Mumbai, India, 8–15 December 2012. find
  5. Danilo Croce, Cristina Giannone, Paolo Annesi, and Roberto Basili. 2010. Towards open-domain semantic role labeling. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 237–246, Uppsala, Sweden, 11–16 July 2010. find
  6. Danilo Croce, Alessandro Moschitti, and Roberto Basili. 2011. Structured lexical similarity via convolution kernels on dependency trees. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pages 1034–1046, Edinburgh, United Kingdom. find
  7. Dipanjan Das and Noah A. Smith. 2011. Semi-supervised frame-semantic parsing for unknown predicates. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, 19–24 June 2011. find our card
  8. Dipanjan Das, Desai Chen, André F. T. Martins, Nathan Schneider, and Noah A. Smith. Frame-Semantic Parsing. Computational Linguistics, 40(1):9–56. find our card
  9. Koen Deschacht and Marie-Francine Moens. 2009. Semi-supervised semantic role labeling using the Latent Words Language Model. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 21–29, Singapore, 2–7 August 2009. find
  10. Georgiana Dinu and Mirella Lapata. 2010. Measuring distributional similarity in context. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 1162–1172, Cambridge, Massachusetts, 9–11 October 2010. find
  11. Charles J. Fillmore. 1976. Frame semantics and the nature of language. In Annals of the New York Academy of Sciences: Conference on the Origin and Development of Language and Speech, volume 280, pages 20– 32. find
  12. William Foland and James Martin. 2015. Dependency-based semantic role labeling using convolutional neural networks. In Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics, pages 279–288, Denver, Colorado. find
  13. Matthew Gerber and Joyce Chai. 2012. Semantic Role Labeling of Implicit Arguments for Nominal Predicates. Computational Linguistics, 38(4):755–798. find
  14. Daniel Gildea and Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28(3):245–288. find our card
  15. Philip Gorinski, Josef Ruppenhofer, and Caroline Sporleder. 2013. Towards weakly supervised resolution of null instantiations. In Proceedings of the 10th International Conference on Computational Semantics (IWCS 2013) – Long Papers, pages 119–130, Potsdam, Germany, 19–22 March 2013. find
  16. Karl Moritz Hermann, Dipanjan Das, Jason Weston, and Kuzman Ganchev. 2014. Semantic frame identification with distributed word representations. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 1448–1458, Baltimore, Maryland, 23–25 June 2014. find
  17. Fei Huang and Alexander Yates. 2010. Open-domain semantic role labeling by modeling word spans. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 968–978, Uppsala, Sweden, 11–16 July 2010. find
  18. Richard Johansson and Pierre Nugues. 2008. The effect of syntactic representation on semantic role labeling. In Proceedings of the 22nd International Conference on Computational Linguistics, pages 393–400, Manchester, United Kingdom, 18–22 August 2008. find
  19. Egoitz Laparra and German Rigau. 2013. Sources of evidence for implicit argument resolution. In Proceed-2014. ings of the 10th International Conference on Computational Semantics (IWCS 2013) – Long Papers, pages 155–166, Potsdam, Germany, 19–22 March 2013. find
  20. Heeyoung Lee, Angel Chang, Yves Peirsman, Nathanael Chambers, Mihai Surdeanu, and Dan Jurafsky. 2013. Deterministic coreference resolution based on entity-centric, precision-ranked rules. Computational Linguistics, 39(4):885–916. find our card
  21. Tao Lei, Yuan Zhang, Lluı́s Màrquez, Alessandro Moschitti, and Regina Barzilay. 2015. High-order low-rank tensors for semantic role labeling. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1150… find
  22. Tomas Mikolov, Wen-tau Yih, and Geoffrey Zweig. 2013. Linguistic regularities in continuous space word representations. In Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 746–751, Atlanta, Georgia,… find
  23. Alessandro Moschitti. 2004. A study on convolution kernels for shallow statistic parsing. In Proceedings of the 42nd Meeting of the Association for Computational Linguistics (ACL’04), Main Volume, pages 335– 342, Barcelona, Spain. find
  24. Sebastian Padó, Marco Pennacchiotti, and Caroline Sporleder. 2008. Semantic role assignment for event nominalisations by leveraging verbal data. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 665– 672, Manchester, United Kingdom. find
  25. Marco Pennacchiotti, Diego De Cao, Roberto Basili, Danilo Croce, and Michael Roth. 2008. Automatic induction of FrameNet lexical units. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 457–465, Honolulu, Hawaii, USA, 25–27 October 2008. find our card
  26. Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 1532–1543, Doha, Qatar, 25–29 October 2014. find
  27. Ralph L Rose. 2011. Joint information value of syntactic and semantic prominence for subsequent pronominal reference. Salience: Multidisciplinary Perspectives on Its Function in Discourse, 227:81–103. find
  28. Michael Roth and Kristian Woodsend. 2014. Composition of word representations improves semantic role labelling. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, pages 407–413, Doha, Qatar, 25–29 October 2014. find
  29. Josef Ruppenhofer, Michael Ellsworth, Miriam R. L. Petruck, Christopher R. Johnson, and Jan Scheffczyk. 2010. FrameNet II: Extended Theory and Practice. Technical report, International Computer Science Institute, 14 September 2010. find
  30. Josef Ruppenhofer, Philip Gorinski, and Caroline Sporleder. 2011. In search of missing arguments: A linguistic approach. In Proceedings of the International Conference Recent Advances in Natural Language Processing 2011, pages 331–338, Hissar, Bulgaria, 12–14 September 2011. find
  31. Magnus Sahlgren. 2008. The distributional hypothesis. Italian Journal of Linguistics, 20(1):33–54. find
  32. Dan Shen and Mirella Lapata. 2007. Using semantic roles to improve question answering. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pages 12–21, Prague, Czech Republic. find
  33. Carina Silberer and Anette Frank. 2012. Casting implicit role linking as an anaphora resolution task. In Proceedings of the First Joint Conference on Lexical and Computational Semantics (*SEM 2012), pages 1–10, Montréal, Canada, 7-8 June. find
  34. Oscar Täckström, Kuzman Ganchev, and Dipanjan Das. 2015. Efficient inference and structured learning for semantic role labeling. Transactions of the Association for Computational Linguistics, 3:29–41. find
  35. Stefan Thater, Hagen Fürstenau, and Manfred Pinkal. 2010. Contextualizing semantic representations using syntactically enriched vector models. In Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, pages 948–957, Uppsala, Sweden, 11–16 July 2010. find
  36. Kristina Toutanova, Aria Haghighi, and Christopher Manning. 2005. Joint learning improves semantic role labeling. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics, pages 589–596, Ann Arbor, Michigan, 29–30 June 2005. find
  37. Boyi Xie, Rebecca J. Passonneau, Leon Wu, and Germán G. Creamer. 2013. Semantic frames to predict stock price movement. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 873–883, Sofia, Bulgaria, 4–9 August 2013. find
  38. Nianwen Xue and Martha Palmer. 2004. Calibrating features for semantic role labeling. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing, pages 88–94, Barcelona, Spain, July. find
  39. Alexander Yeh. 2000. More accurate tests for the statistical significance of result differences. In Proceedings of the 18th International Conference on Computational Linguistics, pages 947–953, Saarbrücken, Germany. find
  40. Beñat Zapirain, Eneko Agirre, Lluı́s Màrquez, and Mihai Surdeanu. 2013. Selectional preferences for semantic role classification. Computational Linguistics, 39(3):631–663. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/roth-2015-context-aware-frame-semantic-role/