Elamur Research
☰
home / papers / 2015 / Parsing English into Abstract Meaning Representation Using Syntax-Based Machine Translation

Parsing English into Abstract Meaning Representation Using Syntax-Based Machine Translation

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/D15-1136.pdf

Summary

The paper addresses AMR parsing: converting English sentences into Abstract Meaning Representation graphs. Instead of designing a custom algorithm, the authors reuse an existing string-to-tree syntax-based machine translation (SBMT) pipeline. This pipeline includes GHKM rule extraction, a bottom-up chart decoder and MIRA tuning. They treat English-to-AMR as a translation task. Because GHKM requires trees, AMR graphs are converted into tree form. This involves dropping extra parents, moving edge labels down to leaves and adding preterminals. The trees are then restructured around role labels, preterminals are relabeled and child nodes are reordered, which exploits the fact that AMR children are unordered. Further additions are a hierarchical AMR-specific language model, semantic resources such as category labels, combined unsupervised and rule-based alignments, and BLEU-based tuning that closely tracks Smatch. When trained and evaluated on the AMR 1.0 corpus, the system achieves better results than two earlier parsers, Wang et al. (2015) and JAMR (Flanigan et al., 2014). The work shows that mature MT infrastructure can be retrained to reach strong semantic parsing results with modest task-specific changes.

Key points

  • The data is the AMR 1.0 corpus (LDC2014T12), covering news and web forums, with a split of 10,313 / 1,368 / 1,371 sentences for train/dev/test (about 218K training tokens). Evaluation uses Smatch 1.0.
  • The only lossy step is cutting multi-parent links. These occur about 1.05 times per training sentence and appear in 48% of training sentences.
  • The flat-tree baseline extracts about 1.43M brittle rules. Role restructuring reduces this to about 661K, and later steps raise it to about 1.31M useful rules in the final system.
  • Each step improves results in turn: restructuring, relabeling and reordering surpass JAMR. Adding the AMR LM and semantic resources beats Wang et al. (2015). Concatenating rule-based and unsupervised alignments gives the best results.
  • The parser is publicly available at amr.isi.edu.

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: Machine translation

Cited by

46 papers of our library cite it (of the 140673 whose bibliographies we read); 8 of them have a page here, 38 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/d15-1136

@inproceedings{pust2015parsing,
  title = {{Parsing English into Abstract Meaning Representation Using Syntax-Based Machine Translation}},
  author = {Pust, Michael and Hermjakob, Ulf and Knight, Kevin and Marcu, Daniel and May, Jonathan},
  booktitle = {Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing},
  year = {2015},
  doi = {10.18653/v1/d15-1136},
  url = {https://doi.org/10.18653/v1/d15-1136}
}

References

40 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jacob Andreas, Andreas Vlachos, and Stephen Clark. 2013. Semantic parsing as machine translation. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 47–52, Sofia, Bulgaria, August. Association for Computational Linguistics. find
  2. Nguyen Bach and Sameer Badaskar. 2007. A Review of Relation Extraction. Unpublished. http://www.cs.cmu.edu/˜nbach/papers/A-survey-on-Relation-Extraction. pdf. ↗
  3. 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, Sofia, Bulgaria, August. Association for Computational Linguistics. find our card
  4. Peter F. Brown, Vincent J. Della Pietra, Stephen A. Della Pietra, and Robert L. Mercer. 1993. The mathematics of statistical machine translation: parameter estimation. Computational Linguistics, 19(2):263–311. find
  5. 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, Sofia, Bulgaria, August. Association for Computational Linguistics. find
  6. Eugene Charniak. 2000. A maximum-entropy-inspired parser. In Proceedings of the 1st North American Chapter of the Association for Computational Linguistics Conference, NAACL 2000, pages 132–139, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  7. Stanley F. Chen and Joshua Goodman. 1996. An empirical study of smoothing techniques for language modeling. In Proceedings of the 34th Annual Meeting on Association for Computational Linguistics, ACL ’96, pages 310–318, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  8. David Chiang, Kevin Knight, and Wei Wang. 2009. 11,001 new features for statistical machine translation. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 218–226, Boulder, Colorado, June. Association for Computational Linguistics. find
  9. Michael Collins. 1997. Three generative, lexicalised models for statistical parsing. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics, pages 16–23, Madrid, Spain, July. Association for Computational Linguistics. find
  10. Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. Bradford Books. find
  11. Jenny Rose Finkel, Trond Grenager, and Christopher Manning. 2005. Incorporating non-local information into information extraction systems by gibbs sampling. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 363–370, Ann Arbor, Michigan, June. Association for Computational Linguistics. find
  12. 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
  13. Michel Galley, Mark Hopkins, Kevin Knight, and Daniel Marcu. 2004. What’s in a translation rule? In Daniel Marcu Susan Dumais and Salim Roukos, editors, HLT-NAACL 2004: Main Proceedings, pages 273–280, Boston, Massachusetts, USA, May 2 - May 7. Association for Computational Linguistics. find our card
  14. Michel Galley, Jonathan Graehl, Kevin Knight, Daniel Marcu, Steve DeNeefe, Wei Wang, and Ignacio Thayer. 2006. Scalable inference and training of context-rich syntactic translation models. In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, pages 961–968, Sydney, Australia, July. Association for Computational Linguistics. find our card
  15. Daniel Gildea and Daniel Jurafsky. 2002. Automatic labeling of semantic roles. Computational Linguistics, 28(3):245–288, September. find our card
  16. Mark Hopkins and Greg Langmead. 2010. SCFG decoding without binarization. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 646–655, Cambridge, MA, October. Association for Computational Linguistics. find
  17. Matthias Huck, Hieu Hoang, and Philipp Koehn. 2014. Augmenting string-to-tree and tree-to-string translation with non-syntactic phrases. In Proceedings of the Ninth Workshop on Statistical Machine Translation, pages 486–498, Baltimore, Maryland, USA, June. Association for Computational Linguistics. find
  18. Bevan Jones, Mark Johnson, and Sharon Goldwater. 2011. Formalizing semantic parsing with tree transducers. In Proceedings of the Australasian Language Technology Association Workshop 2011, pages 19–28, Canberra, Australia, December. find
  19. Bevan Jones, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, and Kevin Knight. 2012a. find
  20. Semantics-based machine translation with hyperedge replacement grammars. In Proceedings of COLING 2012, pages 1359–1376, Mumbai, India, December. find our card
  21. The COLING 2012 Organizing Committee. find
  22. Bevan Jones, Mark Johnson, and Sharon Goldwater. 2012b. Semantic parsing with bayesian tree transducers. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 488–496, Jeju Island, Korea, July. Association for Computational Linguistics. find
  23. Paul Kingsbury and Martha Palmer. 2002. From treebank to propbank. In In Language Resources and Evaluation. find our card
  24. Gregory Kuhlmann, Peter Stone, Raymond J. Mooney, and Jude W. Shavlik. 2004. Guiding a reinforcement learner with natural language advice: Initial results in robocup soccer. In The AAAI-2004 Workshop on Supervisory Control of Learning and Adaptive Systems, July. find
  25. Peng Li, Yang Liu, and Maosong Sun. 2013. An extended ghkm algorithm for inducing lambda-scfg. In Marie desJardins and Michael L. Littman, editors, AAAI. AAAI Press. find
  26. Jonathan May and Kevin Knight. 2007. Syntactic re-alignment models for machine translation. In Jason Eisner and Taku Kudo, editors, Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pages 360–368, Prague, Czech Republic, June 28 – June 30. Association for Computational Linguistics. find
  27. David Nadeau and Satoshi Sekine. 2007. A survey of named entity recognition and classification. Linguisticae Investigationes, 30(1):3–26, January. Publisher: John Benjamins Publishing Company. find
  28. Roberto Navigli. 2009. Word sense disambiguation: A survey. ACM Comput. Surv., 41(2):10:1–10:69, February. find
  29. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: A method for automatic evaluation of machine translation. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL ’02, pages 311–318, Stroudsburg, PA, USA. Association for Computational Linguistics. find our card
  30. Nima Pourdamghani, Yang Gao, Ulf Hermjakob, and Kevin Knight. 2014. Aligning English strings with Abstract Meaning Representation graphs. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 425–429, Doha, Qatar, October. Association for Computational Linguistics. find our card
  31. P. J. Price. 1990. Evaluation of spoken language systems: The ATIS domain. In Proceedings of the Workshop on Speech and Natural Language, HLT ’90, pages 91–95, Stroudsburg, PA, USA. Association for Computational Linguistics. find
  32. Michael Pust and Kevin Knight. 2009. Faster mt decoding through pervasive laziness. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, pages 141–144, Boulder, Colorado, June. Association for Computational Linguistics. find
  33. Wei Wang, Jonathan May, Kevin Knight, and Daniel Marcu. 2010. Re-structuring, re-labeling, and re-aligning for syntax-based machine translation. Computational Linguistics, 36(2):247–277, June. find
  34. Chuan Wang, Nianwen Xue, and Sameer Pradhan. 2015. A transition-based algorithm for amr parsing. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 366–375, Denver, Colorado, May–June. Association for Computational Linguistics. find
  35. Keenon Werling, Gabor Angeli, and Christopher D. Manning. 2015. Robust subgraph generation improves abstract meaning representation parsing. 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 982–991, Beijing, China, July. Association for Computational Linguistics. find
  36. I.H. Witten and T.C. Bell. 1991. The zero-frequency problem: Estimating the probabilities of novel events in adaptive text compression. IEEE Transactions on Information Theory, 37(4). find
  37. Yuk Wah Wong and Raymond Mooney. 2006. Learning for semantic parsing with statistical machine translation. In Proceedings of the Human Language Technology Conference of the NAACL, Main Conference, pages 439–446, New York City, USA, June. Association for Computational Linguistics. find
  38. Yuk Wah Wong and Raymond Mooney. 2007. Learning synchronous grammars for semantic parsing with lambda calculus. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pages 960–967, Prague, Czech Republic, June. Association for Computational Linguistics. find
  39. John M. Zelle and Raymond J. Mooney. 1996. Learning to parse database queries using inductive logic programming. In Proceedings of the Thirteenth National Conference on Artificial Intelligence - Volume 2, AAAI’96, pages 1050–1055. AAAI Press. find
  40. John Marvin Zelle. 1995. Using Inductive Logic Programming to Automate the Construction of Natural Language Parsers. Ph.D. thesis, University of Texas at Austin, Austin, TX, USA. find