Bridging Semantic Frameworks: mapping DRS onto AMR

What it is about

The paper asks how much of an AMR graph can be built from the Discourse Representation Structure of the same sentence (the Parallel Meaning Bank variant). The authors write a hand-made graph rewriting system from DRS to AMR, with a lexicon that maps WordNet senses to PropBank predicates and roles. They annotate 102 sentences into gold AMR for testing and use 95 further sentences to build the rules. Scores are Smatch against gold, compared with two neural AMR parsers trained on far more data. The parsers score higher overall, but the rules recover a large part of the AMR structure. The weak spots are negation and reentrancy. The paper also lists where the two frameworks diverge: quantifiers and scope, definite and demonstrative determiners, and questions.

Ideas

• I1. Keep the sense lexicon as an explicit table with a count of covered senses per entry. The paper finds that a complete sense lexicon moves the score more than any single rule. In tools/translate/meta.rs this suggests counting how many merges are between senses, not words, and reporting that count with each run.
• I2. Allow two correct readings of one sentence. The paper shows a sentence with two valid graphs (universal quantification written as a condition or as a plain AMR). A meta-world that keeps alternative trees for a verse would let the residual choose the author's reading instead of a single parse.
• I3. Report divergence by kind for each pair of authors: how many meta-world differences come from quantifiers, determiners, or questions. That gives a separate measure for each class and a test case for open problem 4 (function words as features of meta tokens).
• I4. Report the rules on dev and on test separately, and list which structures dev did not contain. The paper's gap between the two sets comes from rules built on dev only. The same check applies to any rule set the translator learns from one author.

For Mova

The ideas touch tools/translate (meta.rs for the lexicon and the divergence table, measure.rs for the per-class report) and prag for frame roles. The paper's rule base is hand-made; Mova can use only its count form, in which each rule is a row with a count. The neural parsers are not for Mova. Their scores are only a reference point.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work.

@inproceedings{pavlova2023bridging,
  title = {{Bridging Semantic Frameworks: mapping DRS onto AMR}},
  author = {Pavlova, Siyana and Amblard, Maxime and Guillaume, Bruno},
  booktitle = {Proceedings of the 15th International Conference on Computational Semantics},
  year = {2023},
  url = {https://aclanthology.org/2023.iwcs-1.21/}
}

References

19 references, 5 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Omri Abend and Ari Rappoport. 2013. Universal Conceptual Cognitive Annotation (UCCA). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 228–238, Sofia, Bulgaria. Association for Computational Linguistics. find our card
2. Johan Bos. 2021. Variable-free discourse representation structures. find
3. 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. Association for Computational Linguistics. find
4. Ann Copestake, Dan Flickinger, Carl Pollard, and Ivan A Sag. 2005. Minimal recursion semantics: An introduction. Research on language and computation, 3(2):281–332. find
5. Marco Damonte, Shay B. Cohen, and Giorgio Satta. 2017. An incremental parser for Abstract Meaning Representation. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 536–546, Valencia, Spain. Association for Computational Linguistics. find
6. Lasha Abzianidze, Johannes Bjerva, Kilian Evang, Hessel Haagsma, Rik van Noord, Pierre Ludmann, Duc-Duy Nguyen, and Johan Bos. 2017. The Parallel Meaning Bank: Towards a multilingual corpus of translations annotated with compositional meaning representations. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 242–247, Valencia, Spain. Association for Computational Linguistics. find our card
7. Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. Bradford Books. find
8. Xuefeng Bai, Yulong Chen, and Yue Zhang. 2022. Graph pre-training for AMR parsing and generation. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6001–6015, Dublin, Ireland. Association for Computational Linguistics. find
9. Daniel Hershcovich, Nathan Schneider, Dotan Dvir, Jakob Prange, Miryam de Lhoneux, and Omri Abend. 2020. Comparison by conversion: Reverse-engineering UCCA from syntax and lexical semantics. In Proceedings of the 28th International Conference on Computational Linguistics, pages 2947– 2966, Barcelona, Spain (Online). International Committee on Computational Linguistics. find our card
10. 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. find our card
11. Bruno Guillaume. 2021. Graph matching and graph rewriting: GREW tools for corpus exploration, maintenance and conversion. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 168–175, Online. Association for Computational Linguistics. ↗
12. Hans Kamp and Uwe Reyle. 1993. From discourse to logic: Introduction to modeltheoretic semantics of natural language, formal logic and discourse representation theory. Dordrecht. Kluwer. find
13. Claire Bonial, William Corvey, Martha Palmer, Volha V. Petukhova, and Harry Bunt. 2011. A hierarchical unification of lirics and verbnet semantic roles. In 2011 IEEE Fifth International Conference on Semantic Computing, pages 483–489. IEEE. find
14. Young-Suk Lee, Ramón Astudillo, Hoang Thanh Lam, Tahira Naseem, Radu Florian, and Salim Roukos. 2022. Maximum Bayes Smatch ensemble distillation for AMR parsing. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 5379–5392, Seattle, United States. Association for Computational Linguistics. ↗
15. Johan Bos. 2020. Separating argument structure from logical structure in AMR. In Proceedings of the Second International Workshop on Designing Meaning Reinhard Muskens. 1996. Combining montague semantics and discourse representation. Linguistics and philosophy, pages 143–186. find
16. Guillaume Bonfante, Bruno Guillaume, and Guy Perrier. 2018. Application of Graph Rewriting to Natural Language Processing. Wiley Online Library. find
17. Martha Palmer. 2009. Semlink: Linking propbank, verbnet and framenet. In Proceedings of the generative lexicon conference, pages 9–15. GenLex-09, Pisa, Italy. find
18. 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
19. Noortje Venhuizen. 2015. Projection in Discourse: A data-driven formal semantic analysis. Ph.D. thesis, Rijksuniversiteit Groningen. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/pavlova-2023-bridging-semantic-frameworks-mapping-drs/