Abstract
Abstract meaning representations (AMRs) represent sentence semantics as rooted labeled directed acyclic graphs. Though there is a strong correlation between the AMR graph of a sentence and its corresponding dependency tree, the recent neural network AMR parsers do neglect the exploitation of dependency structure information. In this paper, we explore a novel approach to exploiting dependency structures for AMR parsing. Unlike traditional pipeline models, we treat dependency parsing as an auxiliary task for AMR parsing under the multi-task learning framework by sharing neural network parameters and selectively extracting syntactic representation by the attention mechanism. Particularly, to balance the gradients and focus on the AMR parsing task, we present a new dynamical weighting scheme in the loss function. The experimental results on the LDC2015E86 and LDC2017T10 dataset show that our dependency-auxiliary AMR parser significantly outperforms the baseline and its pipeline counterpart, and demonstrate that the neural AMR parsers can be greatly boosted with the help of effective methods of integrating syntax.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Notes
References
Ballesteros M, Al-Onaizan Y (2017) Amr parsing using stack-lstms. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp 1269–1275
Banarescu L, Bonial C, Cai S, Georgescu M, Griffitt K, Hermjakob U, Knight K, Koehn P, Palmer M, Schneider N (2013) Abstract meaning representation for sembanking. In: Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pp 178–186
Cheng X, Roth D (2013) Relational inference for wikification. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp 1787–1796
Damonte M, Cohen SB, Satta G (2017) An incremental parser for abstract meaning representation. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pp 536–546
Dozat T, Manning CD (2017) Deep biaffine attention for neural dependency parsing. In: Proceedings of the 5th International Conference on Learning Representations
Dozat T, Qi P, Manning C D (2017) Stanford’s graph-based neural dependency parser at the conll 2017 shared task. In: Proceedings of the CoNLL 2017 Shared Task, Multilingual Parsing from Raw Text to Universal Dependencies, pp 20–30
Flanigan J, Thomson S, Carbonell J, Dyer C, Smith N A (2014) A discriminative graph-based parser for the abstract meaning representation. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol 1, pp 1426–1436
Foland W, Martin JH (2017) Abstract meaning representation parsing using lstm recurrent neural networks. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp 463–472
Goodman J, Vlachos A, Naradowsky J (2016) Noise reduction and targeted exploration in imitation learning for abstract meaning representation parsing. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, vol 1, pp 1–11
Hershcovich D, Abend O, Rappoport A (2018) Multitask parsing across semantic representations. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp 373–385
Konstas I, Iyer S, Yatskar M, Choi Y, Zettlemoyer L (2017) Neural amr: Sequence-to-sequence models for parsing and generation. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, pp 146–157
Kuncoro A, Ballesteros M, Kong L, Dyer C, Neubig G, Smith NA (2017) What do recurrent neural network grammars learn about syntax? In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pp 1249–1258
Lyu C, Titov I (2018) Amr parsing as graph prediction with latent alignment. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, pp 397–407
Peters M, Neumann M, Iyyer M, Gardner M, Clark C, Lee K, Zettlemoyer L (2018) Deep contextualized word representations. In: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics, pp 2227–2237
Puzikov Y, Kawahara D, Kurohashi S (2016) M2l at semeval-2016 task 8: Amr parsing with neural networks. In: Proceedings of the 10th international workshop on semantic evaluation (semeval-2016), pp 1154–1159
Qiu J, Liu Y, Chai Y, Si Y, Su S, Wang L, Wu Y (2019) Dependency-based local attention approach to neural machine translation. Comput Mater Cont 59(2):547–562
Strubell E, Verga P, Andor D, Weiss D, McCallum A (2018) Linguistically-informed self-attention for semantic role labeling. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp 5027–5038
van Noord R, Bos J (2017) Neural semantic parsing by character-based translation: Experiments with abstract meaning representations. Comput Linguist Netherlands J 7:93–108
Wang C, Xue N, Pradhan S (2015a) A transition-based algorithm for amr parsing. In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics, pp 366–375
Wang C, Xue N, Pradhan S (2015b) Boosting transition-based amr parsing with refined actions and auxiliary analyzers. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, pp 857–862
Wang C, Xue N (2017) Getting the most out of amr parsing. In: Proceedings of the 2017 conference on empirical methods in natural language processing, pp 1257–1268
Wang S, Zhang L, Zhang Y, Sun J, Pang C, Tian G, Cao N (2018) Natural language semantic construction based on cloud database. Comput Mater Cont 57(3):603–619
Werling K, Angeli G, Manning C D (2015) Robust subgraph generation improves abstract meaning representation parsing. In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics, vol 1, pp 982–991
Xu K, Wu L, Wang Z, Yu M, Chen L, Sheinin V (2018) Exploiting rich syntactic information for semantic parsing with graph-to-sequence model. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp 918–924
Yang K, Wang Y, Zhang W, Yao J, Le Y (2019) Keyphrase generation based on self-attention mechanism. Comput Mater Cont 61(2):569–581
Zhang S, Ma X, Duh K, Durme BV (2019) Amr parsing as sequence-to-graph transduction. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics
Zhou J, Xu F, Uszkoreit H, Weiguang Q, Li R, Gu Y (2016) Amr parsing with an incremental joint model. In: Proceedings of the 2016 conference on empirical methods in natural language processing, pp 680–689
Acknowledgements
This research is supported by projects 61772278 and 61472191 under the National Science Fundatiaon of China, project 18BYY127 under the National Social Science Foundation of China,project for Jiangsu Higher Institutions’ Excellent Innovative Team for Philosophy and Social Sciences (2017STD006).
Author information
Authors and Affiliations
Corresponding authors
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, T., Zhou, J., Qu, W. et al. Improving AMR parsing by exploiting the dependency parsing as an auxiliary task. Multimed Tools Appl 80, 30827–30838 (2021). https://doi.org/10.1007/s11042-020-09967-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-09967-3