Elamur Research⌕
☰
home / papers / 2015 / Broad-coverage CCG Semantic Parsing with AMR

Broad-coverage CCG Semantic Parsing with AMR

Summary

The authors study how to automatically convert sentences from news texts into AMR. AMR is a general-purpose representation of sentence meaning that is not tied to any particular downstream task. Previously, semantic parsers had to be retrained for each application, and they worked only with narrow types of sentences. The AMR Bank corpus made it possible for the first time to train a single model for a broad range of texts. Parsing proceeds in two stages. First, a CCG builds a lambda expression in which some elements are left unfilled. Then a factor graph resolves these elements, in particular by finding what pronouns refer to. For training, the authors developed a new grammar induction algorithm that combines lexical entry templates with recursive splitting, and they also applied an early update strategy. This strategy makes it possible to learn even from partially correct parses. On the test portion of the official LDC release, the system outperformed JAMR by about 3 Smatch F1 points. The gap between automatic methods and human agreement narrowed by 15%. The work shows that CCG is suitable for semantic parsing of open-domain text.

Key points

  • Test results: Smatch F1 is about 66 (66.2 in the abstract, 66.3 in the table), compared with 63.2 for the corrected version of JAMR. Recall improved the most: 65.7 versus 59.2. Inter-annotator agreement is about 83 F1.
  • Entity references: to model references between distant parts of a sentence, the authors use generalized Skolem terms following Steedman (2011). The temporary markers (placeholders) are then resolved by the factor graph.
  • Ablations on the dev set (full system: 66.1 F1):
    • without the second pass with splitting: 65.0 F1, and the lexicon shrinks from 1.6M to 500K entries;
    • without G_gen: 62.6 F1;
    • without surface-form similarity heuristics (JAMR alignments and named-entity matching): 45.6 F1, i.e., a drop of about 20 points.
  • Early update: removing it leaves the model unable to learn from almost half of the training examples, and the score falls by close to 15 points.
  • Open code: the code and trained models are available at yoavartzi.com/amr. Among the open questions, the authors list discontinuous idioms, cross-sentence references, and less reliance on heuristics, so that the method transfers better to other languages.

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 · Machine translation

Topics Syntax & grammar formalisms Semantic parsing & meaning representation

Institutions

🎓University of WashingtonSeattle · United States206 works · 158,423 citations🎓Cornell TechNew York · United States3 works · 1,100 citations

Cite

Cite as Yoav Artzi, Kenton Lee and Luke Zettlemoyer. 2015. Broad-coverage CCG Semantic Parsing with AMR. Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/d15-1198

@inproceedings{artzi2015broad,
  title = {{Broad-coverage CCG Semantic Parsing with AMR}},
  author = {Yoav Artzi, Kenton Lee and Luke Zettlemoyer},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/d15-1198},
  url = {https://doi.org/10.18653/v1/d15-1198}
}

References

46 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Artzi, Y., Das, D., and Petrov, S. (2014). Learning compact lexicons for CCG semantic parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. find
  2. Artzi, Y. and Zettlemoyer, L. S. (2011). Bootstrapping semantic parsers from conversations. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. find
  3. Artzi, Y. and Zettlemoyer, L. S. (2013a). UW SPF: The University of Washington Semantic Parsing Framework. find
  4. Artzi, Y. and Zettlemoyer, L. S. (2013b). Weakly supervised learning of semantic parsers for mapping instructions to actions. Transactions of the Association for Computational Linguistics, 1(1):49–62. our card
  5. Banarescu, L., Bonial, C., Cai, S., Georgescu, M., Griffitt, K., Hermjakob, U., Knight, K., Koehn, P., Palmer, M., and Schneider, N. (2013). Abstract meaning representation for sembanking. In Proceedings of the Linguistic Annotation Workshop. our card
  6. Bos, J. (2008). Wide-coverage semantic analysis with Boxer. In Proceedings of the Conference on Semantics in Text Processing. find
  7. Cai, Q. and Yates, A. (2013). Semantic parsing Freebase: Towards open-domain semantic parsing. In Proceedings of the Joint Conference on Lexical and Computational Semantics. find
  8. Cai, S. and Knight, K. (2013). Smatch: an evaluation metric for semantic feature structures. In Proceedings of the Conference of the Association of Computational Linguistics. find
  9. Chen, D. (2012). Fast online lexicon learning for grounded language acquisition. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. find
  10. Chen, D. L. and Mooney, R. J. (2011). Learning to interpret natural language navigation instructions from observations. In Proceedings of the National Conference on Artificial Intelligence. find
  11. Clark, S. and Curran, J. R. (2007). Wide-coverage efficient statistical parsing with CCG and log-linear models. Computational Linguistics, 33(4):493–552. our card
  12. Clarke, J., Goldwasser, D., Chang, M., and Roth, D. (2010). Driving semantic parsing from the world’s response. In Proceedings of the Conference on Computational Natural Language Learning. find
  13. Collins, M. and Roark, B. (2004). Incremental parsing with the perceptron algorithm. In Proceedings of the Annual Meeting on Association for Computational Linguistics. our card
  14. Duchi, J., Hazan, E., and Singer, Y. (2011). Adaptive subgradient methods for online learning and stochastic optimization. The Journal of Machine Learning Research, pages 2121–2159. find
  15. Flanigan, J., Thomson, S., Carbonell, J., Dyer, C., and Smith, N. A. (2014). A discriminative graph-based parser for the Abstract Meaning Representation. In Proceedings of the Conference of the Association of Computational Linguistics. our card
  16. Goldwasser, D. and Roth, D. (2011). Learning from natural instructions. In Proceedings of the International Joint Conference on Artificial Intelligence. find
  17. Hockenmaier, J. and Bisk, Y. (2010). Normal-form parsing for combinatory categorial grammars with generalized composition and type-raising. In Proceedings of the International Conference on Computational Linguistics. find
  18. Hockenmaier, J. and Steedman, M. (2007). CCG-Bank: A corpus of CCG derivations and dependency structures extracted from the Penn Treebank. Computational Linguistics, pages 355– 396. find
  19. Honnibal, M., Curran, J. R., and Bos, J. (2010). Rebanking CCGBank for Improved NP Interpretation. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. find
  20. Jones, B., Andreas, J., Bauer, D., Hermann, K. M., and Knight, K. (2012). Semantics-based machine translation with hyperedge replacement grammars. In Proceedings of the International Conference on Computational Linguistics. our card
  21. Krishnamurthy, J. and Mitchell, T. (2012). Weakly supervised training of semantic parsers. In Proceedings of the Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. find
  22. Krishnamurthy, J. and Mitchell, T. M. (2015). Learning a compositional semantics for Freebase with an open predicate vocabulary. Transactions of the Association for Computational Linguistics, 3. find
  23. Kwiatkowski, T., Choi, E., Artzi, Y., and Zettlemoyer, L. S. (2013). Scaling semantic parsers with on-the-fly ontology matching. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. our card
  24. Kwiatkowski, T., Goldwater, S., Zettlemoyer, L. S., and Steedman, M. (2012). A probabilistic model of syntactic and semantic acquisition from child-directed utterances and their meanings. Proceedings of the Conference of the European Chapter of the Association of Computational Linguistics. our card
  25. Kwiatkowski, T., Zettlemoyer, L. S., Goldwater, S., and Steedman, M. (2010). Inducing probabilistic CCG grammars from logical form with higher-order unification. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. find
  26. Kwiatkowski, T., Zettlemoyer, L. S., Goldwater, S., and Steedman, M. (2011). Lexical generalization in CCG grammar induction for semantic parsing. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. our card
  27. Lafferty, J., McCallum, A., and Pereira, F. (2001). Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the International Conference on Machine Learning. find
  28. Lewis, M. and Steedman, M. (2013). Combined distributional and logical semantics. Transactions of the Association for Computational Linguistics, 1. find
  29. Lewis, M. and Steedman, M. (2014). A* CCG parsing with a supertag-factored model. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. our card
  30. Liang, P., Jordan, M., and Klein, D. (2011). Learning dependency-based compositional semantics. In Proceedings of the Conference of the Association for Computational Linguistics. find
  31. Liu, F., Flanigan, J., Thomson, S., Sadeh, N., and Smith, N. A. (2015). Toward abstractive summarization using semantic representations. In Proceedings of the North American Association for Computational Linguistics. our card
  32. Manning, C. D., Surdeanu, M., Bauer, J., Finkel, J., Bethard, S. J., and McClosky, D. (2014). The Stanford CoreNLP natural language processing toolkit. In Proceedings of the Annual Meeting of the Association for Computational Linguistics. our card
  33. Muresan, S. (2011). Learning for deep language understanding. In Proceedings of the International Joint Conference on Artificial Intelligence. find
  34. Ng, V. (2010). Supervised noun phrase coreference research: The first fifteen years. In Proceedings of the annual meeting of the association for computational linguistics. our card
  35. Pan, X., Cassidy, T., Hermjakob, U., Ji, H., and Knight, K. (2015). Unsupervised entity linking with Abstract Meaning Representation. In Proceedings of the North American Association for Computational Linguistics. find
  36. Poon, H. (2013). Grounded unsupervised semantic parsing. In Association for Computational Linguistics (ACL). find
  37. Pourdamghani, N., Gao, Y., Hermjakob, U., and Knight, K. (2014). Aligning English strings with Abstract Meaning Representation graphs. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. our card
  38. Ratinov, L. and Roth, D. (2009). Design challenges and misconceptions in named entity recognition. In Proceedings of the Conference on Computational Natural Language Learning. our card
  39. Reddy, S., Lapata, M., and Steedman, M. (2014). Large-scale semantic parsing without question-answer pairs. Transactions of the Association for Computational Linguistics, 2. find
  40. Steedman, M. (1996). Surface Structure and Interpretation. The MIT Press. find
  41. Steedman, M. (2000). The Syntactic Process. The MIT Press. find
  42. Steedman, M. (2011). Taking Scope. The MIT Press. find
  43. Wang, C., Xue, N., Pradhan, S., and Pradhan, S. (2015). A transition-based algorithm for AMR parsing. In Proceedings of the North American Association for Computational Linguistics. our card
  44. Wong, Y. and Mooney, R. J. (2007). Learning synchronous grammars for semantic parsing with lambda calculus. In Proceedings of the Conference of the Association for Computational Linguistics. our card
  45. Zelle, J. and Mooney, R. J. (1996). Learning to parse database queries using inductive logic programming. In Proceedings of the National Conference on Artificial Intelligence. our card
  46. Zettlemoyer, L. S. and Collins, M. (2005). Learning to map sentences to logical form: Structured classification with probabilistic categorial grammars. In Proceedings of the Conference on Uncertainty in Artificial Intelligence. our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/artzi-2015-broad-coverage-ccg-semantic-parsing/