Elamur Research
☰
home / papers / 2015 / Boosting Transition-based AMR Parsing with Refined Actions and Auxiliary Analyzers

Boosting Transition-based AMR Parsing with Refined Actions and Auxiliary Analyzers

Written for the Research library (claude-opus-5-5) from the paper text, in our own words: the license "CC BY-NC-SA 3.0 (ACL Anthology, before 2016)" does not allow redistributing the text itself. Original — aclanthology.org/P15-2141.pdf

Summary

This short paper extends a two-stage transition-based AMR parser (Wang et al., 2015). The parser first produces a dependency tree, then transforms it into an AMR graph through a sequence of actions. The earlier version had no way to produce abstract concepts, which are AMR nodes not aligned to any word, such as have-org-role-91. The authors fix this with a new INFER action that inserts such a concept between the current node and its parent. They also add features from auxiliary tools: semantic roles and framesets from ASSERT and IMS, coreference chains from the Lee et al. (2013) resolver, and Brown clusters. Training uses the averaged perceptron with greedy decoding. On the newswire portion of LDC2013E117, scored with Smatch, the INFER action and SRL features give the largest gains. Brown clusters leave F1 unchanged, and coreference slightly lowers it. The final system beats the strongest previously published parser by 7 F1 points. The advantage holds on LDC2014T12, showing that better actions and richer features matter for AMR parsing. The code is publicly released.

Key points

  • Choice of first-stage parser: Results are stable across first-stage dependency parsers (Stanford, Charniak, Malt, Turbo) trained on Penn Treebank sections 02–22. Charniak retrained on OntoNotes (Charniak (ON)) performs best, with dev F1 0.65.
  • Ablations on the dev set:
    • INFER raises F1 from 0.65 to 0.69.
    • Brown clusters (1000 classes) add recall but no F1.
    • SRL features bring F1 to 0.71.
    • Coreference features drop it to 0.70.
  • LDC2013E117 test results: The split is 4.0K/2.1K/2.1K. The system reaches F1 0.70, compared with 0.63 for JAMR (GitHub) and for Wang et al. (2015), and 0.62 for the Stanford parser.
  • LDC2014T12 results: This dataset has 13,051 AMRs, split 10,312/1,368/1,371. All parsers score lower here, but the system keeps a similar lead.

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: Machine translation

Topics: Coreference resolution · Dependency parsing · Semantic role labeling

Cited by

45 papers of our library cite it (of the 140673 whose bibliographies we read); 4 of them have a page here, 41 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.3115/v1/p15-2141

@inproceedings{wang2015boosting,
  title = {{Boosting Transition-based AMR Parsing with Refined Actions and Auxiliary Analyzers}},
  author = {Wang, Chuan and Xue, Nianwen and Pradhan, Sameer},
  booktitle = {Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)},
  year = {2015},
  doi = {10.3115/v1/p15-2141},
  url = {https://doi.org/10.3115/v1/p15-2141}
}

References

20 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Laura Banarescu, Claire Bonial, Shu Cai, Madalina Georgescu, Kira Griffitt, Ulf Hermjakob, Kevin Knight, Philipp Koehn, Martha Palmer, and Nathan Schneider. 2013. Abstract meaning representation for sembanking. In Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pages 178–186. Association for Computational Linguistics. find our card
  2. Shu Cai and Kevin Knight. 2013. Smatch: an evaluation metric for semantic feature structures. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 748–752. Association for Computational Linguistics. find
  3. Eugene Charniak and Mark Johnson. 2005. Coarse-to-fine n-best parsing and maxent discriminative reranking. In Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL ’05, pages 173–180, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  4. Michael Collins. 2002. Discriminative training methods for hidden markov models: Theory and experiments with perceptron algorithms. In Proceedings of the ACL-02 conference on Empirical methods in natural language processing-Volume 10, pages 1–8. Association for Computational Linguistics. find our card
  5. Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith. 2014. A discriminative graph-based parser for the abstract meaning representation. In Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1426– 1436, Baltimore, Maryland, June. Association for Computational Linguistics. find
  6. Eduard Hovy, Mitchell Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. Ontonotes: the 90% solution. In Proceedings of the human language technology conference of the NAACL, Companion Volume: Short Papers, pages 57–60. Association for Computational Linguistics. find
  7. Terry Koo, Xavier Carreras, and Michael Collins. 2008. Simple semi-supervised dependency parsing. ACL-08: HLT, page 595. find our card
  8. 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
  9. Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven J. Bethard, and David Mc-Closky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 55–60. find our card
  10. Andre Martins, Miguel Almeida, and Noah A. Smith. 2013. Turning on the turbo: Fast third-order non-projective turbo parsers. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 617–622, Sofia, Bulgaria, August. Association for Computational Linguistics. find our card
  11. Ryan McDonald, Fernando Pereira, Kiril Ribarov, and Jan Hajič. 2005. Non-projective dependency parsing using spanning tree algorithms. In Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, HLT ’05, pages 523–530, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  12. Joakim Nivre, Johan Hall, and Jens Nilsson. 2006. Maltparser: A data-driven parser-generator for dependency parsing. In Proceedings of LREC, volume 6, pages 2216–2219. find
  13. Martha Palmer, Daniel Gildea, and Paul Kingsbury. 2005. The proposition bank: An annotated corpus of semantic roles. Computational linguistics, 31(1):71–106. ↗ our card
  14. Xiaochang Peng, Linfeng Song, and Daniel Gildea. 2015. A synchronous hyperedge replacement grammar based approach for AMR parsing. In Proceedings of the Nineteenth Conference on Computational Natural Language Learning. find
  15. Sameer Pradhan, Wayne Ward, Kadri Hacioglu, James Martin, and Dan Jurafsky. 2004. Shallow semantic parsing using support vector machines. In Proceedings of the Human Language Technology Conference/North American chapter of the Association of Computational Linguistics (HLT/NAACL), Boston, MA, May. find
  16. Sameer Pradhan, 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, August. find
  17. Joseph Turian, Lev Ratinov, and Yoshua Bengio. 2010. Word representations: a simple and general method for semi-supervised learning. In Proceedings of the 48th annual meeting of the association for computational linguistics, pages 384–394. Association for Computational Linguistics. find our card
  18. Chuan Wang, Nianwen Xue, and Sameer Pradhan. 2015. A transition-based algorithm for AMR parsing. In North American Association for Computational Linguistics, Denver, Colorado. find
  19. Keenon Werling, Gabor Angeli, Melvin Johnson Premkumar, and Christopher D. Manning. 2015. Robust subgraph generation improves abstract meaning representation parsing. In ACL. find
  20. Zhi Zhong and Hwee Tou Ng. 2010. It makes sense: A wide-coverage word sense disambiguation system for free text. In Proceedings of the ACL 2010 System Demonstrations, pages 78–83, Uppsala, Sweden. find