Elamur Research⌕
☰
home / papers / 2021 / Syntax Role for Neural Semantic Role Labeling

Syntax Role for Neural Semantic Role Labeling

Paper · 2021 · Zuchao Li, Hai Zhao, Shexia He et al.

Summary

Early neural SRL systems matched or beat syntax-heavy models without any parse input, so it became unclear whether syntax still matters for semantic role labeling. The authors test this systematically for both span-style and dependency-style SRL, in English and in the other languages of the CoNLL-2005, CoNLL-2009 and CoNLL-2012 benchmarks. They build three baseline families: sequence-based, tree-based and graph-based. Each one receives syntax in one of two ways: pruning candidate arguments with the parse, or feeding parse features to the encoder. Runs are made with and without predicates given, with parses of different quality, and with or without pre-trained encoders such as ELMo and BERT. To compare systems built on different parsers fairly, they divide semantic F1 by the parser's LAS or constituent F1. Syntax still helps under some conditions, but the gain shrinks as the base model gets stronger. In the best settings it is roughly half a point, compared with 5–10 points before neural models. Hard pruning suits deep models poorly. This matters for deciding whether an explicit parser is worth running before role labeling.

Key points

  • Benchmarks: CoNLL-2005 and CoNLL-2012 for span SRL and CoNLL-2009 for dependency SRL, using every available language.
  • Design: three architectures (sequence, tree, graph) are crossed with two integration styles (syntax pruning and syntax features), tested with and without gold predicates.
  • Metric: Sem-F1 divided by LAS, or by constituent F1, following the CoNLL-2008 shared task, so that parser quality does not distort the comparison.
  • Result: in the strongest setups syntax adds about 0.5% absolute. Pre-NN systems gained around 5–10%, and adding ELMo or BERT shrinks the benefit further.
  • Here "syntax" means only dependency and constituency relations; lemmas and POS tags are excluded. The authors conclude that how syntax is integrated matters more than which model or which kind of syntax is used.

Interesting ideas

  • I1. Normalize a downstream score by the quality of its upstream input (Sem-F1/LAS), so that a system is credited for using its parse well rather than for having a better parser.
  • I2. Treat syntax use as a factorial experiment, with several architectures crossed with several integration methods, instead of judging one model in isolation.
  • I3. Hard pruning of argument candidates with the parse can hurt learned models, because parser errors remove the correct argument before the model ever sees it.
  • I4. Many predicate–argument arcs mirror dependency arcs almost deterministically, so tree relations carry much of the role signal.
  • I5. Strong pre-trained encoders already hold much syntax, so explicit parse features become partly redundant.

For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

  • I1 (learn): report frame-accuracy divided by tree LAS when comparing perceptron and gparse pipelines, so frame-stage improvements are not confused with parser gains.
  • I2 (learn): evaluate VerbNet role assignment under gold trees, silver trees and degraded trees to see how much of frame quality truly comes from the tree.
  • I3 (frames): use tree-based argument candidate filters as soft scores or ranked preferences rather than hard cuts, and log which true arguments a cut would have lost.
  • I4 (frames): seed explainable role rules from UD relation-to-role mappings (nsubj→agent-like, obj→theme-like) and let exceptions surface as repair rules.
  • I5 (tree): when gparse's transformer is strong, measure whether extra tree features still help downstream, and keep the tree mainly for explainability rather than assumed accuracy.

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

🎓Shanghai Jiao Tong UniversityShanghai · China63 works · 15,047 citations

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 9,085 worksArtificial Intelligence · 8,888 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 works

🧭 Topics 3Research subjects and languages the work is about.English · 1,373 worksSemantic role labeling · 132 worksSyntax & grammar formalisms · 162 works

Cite

Cite as Zuchao Li, Hai Zhao, Shexia He and Jiaxun Cai. 2021. Syntax Role for Neural Semantic Role Labeling. Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/coli_a_00408

@article{li2021syntax,
  title = {{Syntax Role for Neural Semantic Role Labeling}},
  author = {Zuchao Li, Hai Zhao, Shexia He and Jiaxun Cai},
  journal = {Computational Linguistics},
  year = {2021},
  doi = {10.1162/coli\_a\_00408},
  url = {https://doi.org/10.1162/coli_a_00408}
}

References

101 references, 43 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Bahdanau, Dzmitry, Kyunghyun Cho, and Yoshua Bengio. 2015. Neural machine translation by jointly learning to align and translate. In 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings, San Diego, CA. ↗
  2. Baker, Collin F., Charles J. Fillmore, and John B. Lowe. 1998. The Berkeley FrameNet project. In 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics, Volume 1, pages 86–90, Montreal.
  3. Berant, Jonathan, Andrew Chou, Roy Frostig, and Percy Liang. 2013. Semantic parsing on Freebase from question-answer pairs. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1533–1544, Seattle, WA.
  4. Björkelund, Anders, Bernd Bohnet, Love Hafdell, and Pierre Nugues. 2010. A high-performance syntactic and semantic dependency parser. In Coling 2010: Demonstrations, pages 33–36, Beijing, China. find
  5. Björkelund, Anders, Love Hafdell, and Pierre Nugues. 2009. Multilingual semantic role labeling. In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task, pages 43–48, Boulder, CO.
  6. Cai, Jiaxun, Shexia He, Zuchao Li, and Hai Zhao. 2018. A full end-to-end semantic role labeler, syntactic-agnostic over syntactic-aware? In Proceedings of the 27th International Conference on Computational Linguistics, pages 2753–2765, Santa Fe, NM. find
  7. Cai, Rui and Mirella Lapata. 2019a. Semi-supervised semantic role labeling with cross-view training. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1018–1027, Hong Kong. find
  8. Cai, Rui and Mirella Lapata. 2019b. Syntax-aware semantic role labeling without parsing. Transactions of the Association for Computational Linguistics, 7:343–356. ↗
  9. Carreras, Xavier and Lluı́s Màrquez. 2005. Introduction to the CoNLL-2005 shared task: Semantic role labeling. In Proceedings of the Ninth Conference on Computational Natural Language Learning (CoNLL-2005), pages 152–164, Ann Arbor, MI.
  10. Chen, Xinchi, Chunchuan Lyu, and Ivan Titov. 2019. Capturing argument interaction in semantic role labeling with capsule networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5415–5425, Hong Kong. ↗
  11. Choe, Do Kook and Eugene Charniak. 2016. Parsing as language modeling. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2331–2336, Austin, TX. find
  12. Choi, Jinho D. and Martha Palmer. 2011. Transition-based semantic role labeling using predicate argument clustering. In Proceedings of the ACL 2011 Workshop on Relational Models of Semantics, pages 37–45, Portland, OR. find
  13. Chomsky, Noam. 1965. Aspects of the Theory of Syntax, volume 11. find
  14. Clark, Kevin, Urvashi Khandelwal, Omer Levy, and Christopher D. Manning. 2019. What does BERT look at? An analysis of BERT’s attention. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 276–286, Florence. find
  15. Collobert, Ronan, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. Journal of Machine Learning Research, 12:2493–2537.
  16. Devlin, Jacob, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, MN.
  17. Dowty, David. 1991. Thematic proto-roles and argument selection. Language, 67(3):547–619. https://doi.org/10.2307/415037, https://doi.org/10.1353/lan .1991.0021 ↗
  18. Dozat, Timothy and Christopher D. Manning. 2017. Deep biaffine attention for neural dependency parsing. In 5th International Conference on Learning Representations, ICLR 2017, Conference Track Proceedings, Toulon.
  19. Fei, Hao, Meishan Zhang, Bobo Li, and Donghong Ji. 2021. End-to-end semantic role labeling with neural transition-based model. In Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Thirty-Third Conference on Innovative Applications of Artificial Intelligence, IAAI 2021, The Eleventh Symposium on Educational Advances in Artificial Intelligence, EAAI 2021, Virtual Event, pages 12803–12811, AAAI Press. find
  20. Fillmore, C. J. 1968. The case for case. Universals in Linguistic Theory. pages 1–9. find
  21. FitzGerald, Nicholas, Oscar Täckström, Kuzman Ganchev, and Dipanjan Das. 2015. Semantic role labeling with neural network factors. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 960–970, Lisbon. find
  22. Foland, William 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, CO. find
  23. Gildea, Daniel and Daniel Jurafsky. 2000. Automatic labeling of semantic roles. In Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics, pages 512–520, Hong Kong.
  24. Gildea, Daniel and Martha Palmer. 2002. The necessity of parsing for predicate argument recognition. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pages 239–246, Philadelphia, PA.
  25. Gómez-Rodrı́guez, Carlos and David Vilares. 2018. Constituent parsing as sequence labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1314–1324, Brussels. find
  26. Grave, Edouard, Piotr Bojanowski, Prakhar Gupta, Armand Joulin, and Tomas Mikolov. 2018. Learning word vectors for 157 languages. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki.
  27. Hajič, Jan, Massimiliano Ciaramita, Richard Johansson, Daisuke Kawahara, Maria Antònia Martı́, Lluı́s Màrquez, Adam Meyers, Joakim Nivre, Sebastian Padó, Jan Štěpánek, Pavel Straňák, Mihai Surdeanu, Nianwen Xue, and Yi Zhang. 2009. The CoNLL-2009 shared task: Syntactic and semantic dependencies in multiple languages. In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task, pages 1–18, Boulder, CO.
  28. He, Luheng, Kenton Lee, Omer Levy, and Luke Zettlemoyer. 2018a. Jointly predicting predicates and arguments in neural semantic role labeling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 364–369, Melbourne.
  29. He, Luheng, Kenton Lee, Mike Lewis, and Luke Zettlemoyer. 2017. Deep semantic role labeling: What works and what’s next. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 473–483, Vancouver.
  30. He, Shexia, Zuchao Li, and Hai Zhao. 2019. Syntax-aware multilingual semantic role labeling. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5350–5359, Hong Kong. ↗
  31. He, Shexia, Zuchao Li, Hai Zhao, and Hongxiao Bai. 2018b. Syntax for semantic role labeling, to be, or not to be. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2061–2071, Melbourne.
  32. Hewitt, John and Christopher D. Manning. 2019. A structural probe for finding syntax in word representations. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4129–4138, Minneapolis, MN.
  33. Hochreiter, Sepp and Jürgen Schmidhuber. 1997. Long short-term memory. Neural Computation, 9(8):1735–1780. https://doi.org/10.1162/neco.1997.9.8 .1735 ↗
  34. Johansson, Richard and Pierre Nugues. 2008a. Dependency-based semantic role labeling of PropBank. In Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, pages 69–78, Honolulu, HI.
  35. Johansson, Richard and Pierre Nugues. 2008b. Dependency-based syntactic–semantic analysis with PropBank and NomBank. In CoNLL 2008: Proceedings of the Twelfth Conference on Computational Natural Language Learning, pages 183–187, Manchester. find
  36. Johansson, Richard and Pierre Nugues. 2008c. The effect of syntactic representation on semantic role labeling. In Proceedings of the 22nd International Conference on Computational Linguistics (Coling 2008), pages 393–400, Manchester, UK. find
  37. Kasai, Jungo, Dan Friedman, Robert Frank, Dragomir Radev, and Owen Rambow. 2019. Syntax-aware neural semantic role labeling with supertags. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 701–709, Minneapolis, MN. ↗
  38. Kingma, Diederik P. and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings, San Diego, CA. ↗
  39. Kiperwasser, Eliyahu and Yoav Goldberg. 2016. Simple and accurate dependency parsing using bidirectional LSTM feature representations. Transactions of the Association for Computational Linguistics, 4:313–327. https://doi.org/10.1162/tacl a 00101 ↗
  40. Kipf, Thomas N. and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In 5th International Conference on Learning Representations, ICLR 2017, Conference Track Proceedings, Toulon. ↗
  41. Kitaev, Nikita and Dan Klein. 2018. Constituency parsing with a self-attentive encoder. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2676–2686, Melbourne.
  42. Lan, Zhenzhong, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2020. ALBERT: A lite BERT for self-supervised learning of language representations. In 8th International Conference on Learning Representations, ICLR 2020, Addis Ababa. find
  43. Lang, Joel and Mirella Lapata. 2010. Unsupervised induction of semantic roles. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 939–947, Los Angeles, CA. find
  44. Lee, Kenton, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen.
  45. Lei, Tao, 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 1150–1160, Denver, CO. find
  46. Levin, Beth. 1993. English Verb Classes and Alternations: A Preliminary Investigation, University of Chicago Press. find
  47. Li, Zuchao, Shexia He, Jiaxun Cai, Zhuosheng Zhang, Hai Zhao, Gongshen Liu, Linlin Li, and Luo Si. 2018. A unified syntax-aware framework for semantic role labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2401–2411, Brussels. find
  48. Li, Zuchao, Shexia He, Hai Zhao, Yiqing Zhang, Zhuosheng Zhang, Xi Zhou, and Xiang Zhou. 2019a. Dependency or span, end-to-end uniform semantic role labeling. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 6730–6737. find
  49. Li, Zuchao, Shexia He, Junru Zhou, Hai Zhao, Kevin Parnow, and Rui Wang. 2019b. Dependency and span, cross-style semantic role labeling on PropBank and NomBank. arXiv preprint arXiv:1911.02851. ↗
  50. Li, Zuchao, Hai Zhao, Rui Wang, and Kevin Parnow. 2020. High-order semantic role labeling. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 1134–1151, Online. find
  51. Lin, Yankai, Zhiyuan Liu, and Maosong Sun. 2017. Neural relation extraction with multi-lingual attention. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 34–43, Vancouver. find
  52. Liu, Yinhan, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692. ↗
  53. Luong, Thang, Hieu Pham, and Christopher D. Manning. 2015. Effective approaches to attention-based neural machine translation. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1412–1421, Lisbon. ↗
  54. Lyu, Chunchuan, Shay B. Cohen, and Ivan Titov. 2019. Semantic role labeling with iterative structure refinement. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1071–1082, Hong Kong. ↗
  55. Marcheggiani, Diego, Anton Frolov, and Ivan Titov. 2017. A simple and accurate syntax-agnostic neural model for dependency-based semantic role labeling. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), pages 411–420, Vancouver.
  56. Marcheggiani, Diego and Ivan Titov. 2017. Encoding sentences with graph convolutional networks for semantic role labeling. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1506–1515, Copenhagen.
  57. Marcheggiani, Diego and Ivan Titov. 2020. Graph convolutions over constituent trees for syntax-aware semantic role labeling. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 3915–3928, Online. find
  58. Mihaylov, Todor and Anette Frank. 2016. Discourse relation sense classification using cross-argument semantic similarity based on word embeddings. In Proceedings of the CoNLL-16 Shared Task, pages 100–107, Berlin.
  59. Moschitti, Alessandro, Daniele Pighin, and Roberto Basili. 2008. Tree kernels for semantic role labeling. Computational Linguistics, 34(2):193–224. https://doi.org/10.1162/coli.2008.34.2.193 ↗
  60. Mulcaire, Phoebe, Swabha Swayamdipta, and Noah A. Smith. 2018. Polyglot semantic role labeling. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 667–672, Melbourne. find
  61. Munir, Kashif, Hai Zhao, and Zuchao Li. 2021. Adaptive convolution for semantic role labeling. IEEE ACM Transactions on Audio, Speech, and Language Processing, 29:782–791. https://doi.org/10.1109/TASLP.2020.3048665 ↗
  62. Nair, Vinod and Geoffrey E. Hinton. 2010. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), pages 807–814, Haifa. find
  63. Naradowsky, Jason, Sebastian Riedel, and David Smith. 2012. Improving NLP through marginalization of hidden syntactic structure. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 810–820, Jeju Island. find
  64. Ouchi, Hiroki, Hiroyuki Shindo, and Yuji Matsumoto. 2018. A span selection model for semantic role labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 1630–1642, Brussels. find
  65. Palmer, Martha, Daniel Gildea, and Paul Kingsbury. 2005. The Proposition Bank: An annotated corpus of semantic roles. Computational Linguistics, 31(1):71–106. https://doi.org/10.1162/0891201053630264 ↗
  66. Peng, Hao, Sam Thomson, Swabha Swayamdipta, and Noah A. Smith. 2018. Learning joint semantic parsers from disjoint data. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1492–1502, New Orleans, LA. ↗
  67. Pennington, Jeffrey, 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 (EMNLP), pages 1532–1543, Doha.
  68. Peters, Matthew, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 2227–2237, New Orleans, LA.
  69. Pradhan, Sameer, Alessandro Moschitti, Nianwen Xue, Hwee Tou Ng, Anders Björkelund, Olga Uryupina, Yuchen Zhang, and Zhi Zhong. 2013. Towards robust linguistic analysis using OntoNotes. In Proceedings of the Seventeenth Conference on Computational Natural Language Learning, pages 143–152, Sofia, Bulgaria. find
  70. Pradhan, Sameer, Alessandro Moschitti, Nianwen Xue, Olga Uryupina, and Yuchen Zhang. 2012. CoNLL-2012 shared task: Modeling multilingual unrestricted coreference in OntoNotes. In Joint Conference on EMNLP and CoNLL - Shared Task, pages 1–40, Jeju Island.
  71. Pradhan, Sameer, Wayne Ward, Kadri Hacioglu, James Martin, and Daniel Jurafsky. 2005. Semantic role labeling using different syntactic views. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 581–588, Ann Arbor, MI. find
  72. Punyakanok, Vasin, Dan Roth, and Wen-tau Yih. 2005. The necessity of syntactic parsing for semantic role labeling. In IJCAI, volume 5, pages 1117–1123. https://doi.org/10.1162/coli.2008.34.2.257 ↗
  73. Punyakanok, Vasin, Dan Roth, and Wen-tau Yih. 2008. The importance of syntactic parsing and inference in semantic role labeling. Computational Linguistics, 34(2):257–287. ↗
  74. Qian, Feng, Lei Sha, Baobao Chang, Lu-chen Liu, and Ming Zhang. 2017. Syntax aware LSTM model for semantic role labeling. In Proceedings of the 2nd Workshop on Structured Prediction for Natural Language Processing, pages 27–32, Copenhagen. ↗
  75. Roth, Michael and Mirella Lapata. 2016. Neural semantic role labeling with dependency path embeddings. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1192–1202, Berlin. ↗
  76. Shi, Chen, Shujie Liu, Shuo Ren, Shi Feng, Mu Li, Ming Zhou, Xu Sun, and Houfeng Wang. 2016. Knowledge-based semantic embedding for machine translation. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2245–2254, Berlin. ↗
  77. Socher, Richard, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1631–1642, Seattle, WA. find
  78. Strubell, Emma, Patrick Verga, Daniel Andor, David Weiss, and Andrew McCallum. 2018. Linguistically-informed self-attention for semantic role labeling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5027–5038, Brussels.
  79. Surdeanu, Mihai, Richard Johansson, Adam Meyers, Lluı́s Màrquez, and Joakim Nivre. 2008. find
  80. The CoNLL 2008 shared task on joint parsing of syntactic and semantic dependencies. In CoNLL 2008: Proceedings of the Twelfth Conference on Computational Natural Language Learning, pages 159–177, Manchester.
  81. Sutskever, Ilya, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014, pages 3104–3112, Montreal. ↗
  82. Swayamdipta, Swabha, Miguel Ballesteros, Chris Dyer, and Noah A. Smith. 2016. Greedy, joint syntactic-semantic parsing with stack LSTMs. In Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, pages 187–197, Berlin. find
  83. Täckström, Oscar, 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. https://doi.org/10.1162/tacl a 00120 ↗
  84. Tai, Kai Sheng, Richard Socher, and Christopher D. Manning. 2015. Improved semantic representations from tree-structured long short-term memory networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1556–1566, Beijing. find
  85. Tan, Zhixing, Mingxuan Wang, Jun Xie, Yidong Chen, and Xiaodong Shi. 2018. Deep semantic role labeling with self-attention. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), the 30th Innovative Applications of Artificial Intelligence (IAAI-18), and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018, pages 4929–4936, AAAI Press.
  86. Toutanova, Kristina, Aria Haghighi, and Christopher D. Manning. 2008. A global joint model for semantic role labeling. Computational Linguistics, 34(2):161–191. https://doi.org/10.1162/coli.2008 .34.2.161 ↗
  87. Vinyals, Oriol, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey E. Hinton. 2015. Grammar as a foreign language. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, pages 2773–2781, Montreal. ↗
  88. Wang, Yufei, Mark Johnson, Stephen Wan, Yifang Sun, and Wei Wang. 2019. How to best use syntax in semantic role labelling. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5338–5343, Florence. find
  89. Xue, Nianwen 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. find
  90. Yang, Bishan and Tom Mitchell. 2017. A joint sequential and relational model for frame-semantic parsing. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 1247–1256, Copenhagen.
  91. Yang, Zhilin, Zihang Dai, Yiming Yang, Jaime G. Carbonell, Ruslan Salakhutdinov, and Quoc V. Le. 2019. Xlnet: Generalized autoregressive pretraining for language understanding. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, pages 5754–5764, Vancouver. ↗
  92. Yih, Wen tau, Matthew Richardson, Chris Meek, Ming-Wei Chang, and Jina Suh. 2016. The value of semantic parse labeling for knowledge base question answering. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 201–206, Berlin.
  93. Zhang, Yue, Rui Wang, and Luo Si. 2019. Syntax-enhanced self-attention-based semantic role labeling. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 616–626, Hong Kong. ↗
  94. Zhao, Hai, Wenliang Chen, Jun’ichi Kazama, Kiyotaka Uchimoto, and Kentaro Torisawa. 2009a. Multilingual dependency learning: Exploiting rich features for tagging syntactic and semantic dependencies. In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task, pages 61–66, Boulder, CO. find
  95. Zhao, Hai, Wenliang Chen, and Chunyu Kit. 2009. Semantic dependency parsing of NomBank and PropBank: An efficient integrated approach via a large-scale feature selection. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 30–39, Singapore.
  96. Zhao, Hai, Wenliang Chen, Chunyu Kit, and Guodong Zhou. 2009b. Multilingual dependency learning: A huge feature engineering method to semantic dependency parsing. In Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task, pages 55–60, Boulder, CO. find
  97. Zhao, Hai and Chunyu Kit. 2008. Parsing syntactic and semantic dependencies with two single-stage maximum entropy models. In CoNLL 2008: Proceedings of the Twelfth Conference on Computational Natural Language Learning, pages 203–207, Manchester, UK. find
  98. Zhao, Hai, Xiaotian Zhang, and Chunyu Kit. 2013. Integrative semantic dependency parsing via efficient large-scale feature selection. Journal of Artificial Intelligence Research, 46:203–233. ↗
  99. Zhou, Junru, Zuchao Li, and Hai Zhao. 2020. Parsing all: Syntax and semantics, dependencies and spans. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4438–4449, Online. find
  100. Zhou, Jie and Wei Xu. 2015. End-to-end learning of semantic role labeling using recurrent neural networks. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1127–1137, Beijing.
  101. Zhou, Junru and Hai Zhao. 2019. Head-Driven Phrase Structure Grammar parsing on Penn Treebank. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 2396–2408, Florence.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/li-2021-syntax-role-neural-semantic-role/