AMR-to-text Generation with Synchronous Node Replacement Grammar

What it is about

The paper generates sentences directly from the AMR graph, without first making a spanning tree, so that no information is lost in the graph-to-tree step. A synchronous node replacement grammar is learned from aligned AMR and sentence pairs. Initial graph-to-string rules come from a phrase-to-fragment extraction; a rule is then collapsed with another when the first contains the second, which replaces the inner fragment with a nonterminal. At test time a bottom-up beam search applies the rules, scored by a log-linear model with translation probabilities, a language model, a reordering model and a moving-distance feature. On the LDC2015E86 test set the system reaches 25.62 BLEU. Removing the induced rules drops it to 17.43, the largest drop in the ablations; removing the moving distance drops it to 24.06. About 30% of the rules used for the best output are glue rules.

Ideas

• I1. Collapse rules by count: for every pair of extracted meta-token fragments where one contains the other, create a collapsed rule with the inner part replaced by a slot. This is a deterministic, count-based way to build nested context tables in profile.rs. Count how many collapsed rules the translator uses on dev.
• I2. A moving-distance analogue: penalise a large jump in the reading order between two consecutive matched fragments. The paper shows this matters (24.06 without it against 25.62). For the translator's output order, measure the same penalty on the Bible pairs.
• I3. Mirror the largest ablation: run the translator with the learned context rules removed, and report the drop beside the author deltas. The result says how much the learned layer carries.
• I4. Report the share of output produced by fallback rules (glue) against learned rules. The same count tells how much of the translator's output comes from the standard path and how much from fallback.

For Mova

The ideas fit tools/translate/profile.rs (rule use and fallback), tools/translate/measure.rs (the ablation table) and en/src/lin.rs (reordering). The paper's reordering model is a count of monotone against inverse order by edge label, which can be a BTreeMap in lin.rs and checked for identical output.

Topics: Machine translation

Cite

The paper itself, not this card. BibTeX from the library's record of the work. DOI 10.18653/v1/p17-2002

@inproceedings{song2017amr,
  title = {{AMR-to-text Generation with Synchronous Node Replacement Grammar}},
  author = {Song, Linfeng and Peng, Xiaochang and Zhang, Yue and Wang, Zhiguo and Gildea, Daniel},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  year = {2017},
  doi = {10.18653/v1/p17-2002},
  url = {https://doi.org/10.18653/v1/p17-2002}
}

References

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

1. Liang Huang, Kevin Knight, and Aravind Joshi. 2006. Statistical syntax-directed translation with extended domain of locality. In Proceedings of Association for Machine Translation in the Americas (AMTA-2006). pages 66–73. find our card
2. Yoav Artzi, Kenton Lee, and Luke Zettlemoyer. 2015. Broad-coverage CCG semantic parsing with AMR. In Conference on Empirical Methods in Natural Language Processing (EMNLP-15). pages 1699– 1710. find
3. Bevan Jones, Jacob Andreas, Daniel Bauer, Karl Moritz Hermann, and Kevin Knight. 2012. Semantics-based machine translation with hyperedge replacement grammars. In Proceedings of the International Conference on Computational Linguistics (COLING-12). pages 1359–1376. find our card
4. 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
5. Philipp Koehn, Franz Josef Och, and Daniel Marcu. 2003. Statistical phrase-based translation. In Proceedings of the 2003 Meeting of the North American chapter of the Association for Computational Linguistics (NAACL-03). pages 48–54. find
6. David Chiang. 2005. A hierarchical phrase-based model for statistical machine translation. In Proceedings of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL-05). Ann Arbor, Michigan, pages 263–270. find our card
7. Xiang Li, Thien Huu Nguyen, Kai Cao, and Ralph Grishman. 2015. Improving event detection with abstract meaning representation. In Proceedings of the First Workshop on Computing News Storylines. Beijing, China, pages 11–15. find
8. Frank Drewes, Hans-Jörg Kreowski, and Annegret Habel. 1997. Hyperedge replacement, graph grammars. Handbook of Graph Grammars 1:95–162. find
9. Yang Liu, Qun Liu, and Shouxun Lin. 2006. Tree-to-string alignment template for statistical machine translation. In Proceedings of the 44th Annual Meeting of the Association for Computational Linguistics (ACL-06). Sydney, Australia, pages 609–616. find our card
10. J. Engelfriet and G. Rozenberg. 1997. Node replacement graph grammars. In Grzegorz Rozenberg, editor, Handbook of Graph Grammars and Computing by Graph Transformation, World Scientific Publishing Co., Inc., River Edge, NJ, USA, pages 1–94. find
11. Fandong Meng, Jun Xie, Linfeng Song, Yajuan Lü, and Qun Liu. 2013. Translation with source constituency and dependency trees. In Conference on Empirical Methods in Natural Language Processing (EMNLP-13). Seattle, Washington, USA, pages 1066–1076. find
12. Jeffrey Flanigan, Chris Dyer, Noah A. Smith, and Jaime Carbonell. 2016. Generation from abstract meaning representation using tree transducers. In Proceedings of the 2016 Meeting of the North American chapter of the Association for Computational Linguistics (NAACL-16). pages 731–739. find our card
13. Arindam Mitra and Chitta Baral. 2015. Addressing a question answering challenge by combining statistical methods with inductive rule learning and reasoning. In Proceedings of the National Conference on Artificial Intelligence (AAAI-16). find
14. 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 (ACL-14). pages 1426–1436. find
15. Franz Josef Och. 2003. Minimum error rate training in statistical machine translation. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics (ACL-03). Sapporo, Japan, pages 160–167. find
16. Daniel Gildea. 2003. Loosely tree-based alignment for machine translation. In Proceedings of the 41th Annual Conference of the Association for Computational Linguistics (ACL-03). Sapporo, Japan, pages 80–87. find
17. 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 of the Association for Computational Linguistics (ACL-02). pages 311–318. find our card
18. James Goodman, Andreas Vlachos, and Jason Naradowsky. 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 (ACL-16). Berlin, Germany, pages 1–11. find
19. 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 (CoNLL-15). pages 731–739. find
20. Jonas Groschwitz, Alexander Koller, and Christoph Teichmann. 2015. Graph parsing with s-graph grammars. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics (ACL-15). Beijing, China, pages 1481–1490. find
21. Xiaochang Peng, Chuan Wang, Daniel Gildea, and Nianwen Xue. 2017. Addressing the data sparsity issue in neural amr parsing. In Proceedings of the Kenji Yamada and Kevin Knight. 2002. A decoder for syntax-based statistical MT. In Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics (ACL-02). Philadelphia, Pennsylvania, USA, pages 303–310. 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL-17). Valencia, Spain, pages 366–375. find
22. Nima Pourdamghani, Kevin Knight, and Ulf Hermjakob. 2016. Generating English from abstract meaning representations. In International Conference on Natural Language Generation (INLG-16). Edinburgh, UK, pages 21–25. find our card
23. Junsheng Zhou, Feiyu Xu, Hans Uszkoreit, Weiguang QU, Ran Li, and Yanhui Gu. 2016. AMR parsing with an incremental joint model. In Conference on Empirical Methods in Natural Language Processing (EMNLP-16). Austin, Texas, pages 680–689. find
24. Michael Pust, Ulf Hermjakob, Kevin Knight, Daniel Marcu, and Jonathan May. 2015. Parsing English into abstract meaning representation using syntax-based machine translation. In Conference on Empirical Methods in Natural Language Processing (EMNLP-15). pages 1143–1154. find
25. Libin Shen, Jinxi Xu, and Ralph Weischedel. 2008. A new string-to-dependency machine translation algorithm with a target dependency language model. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics (ACL-08). Columbus, Ohio, pages 577–585. find our card
26. Linfeng Song, Yue Zhang, Xiaochang Peng, Zhiguo Wang, and Daniel Gildea. 2016. AMR-to-text generation as a traveling salesman problem. In Conference on Empirical Methods in Natural Language Processing (EMNLP-16). Austin, Texas, pages 2084–2089. find
27. Sho Takase, Jun Suzuki, Naoaki Okazaki, Tsutomu Hirao, and Masaaki Nagata. 2016. Neural headline generation on abstract meaning representation. In Conference on Empirical Methods in Natural Language Processing (EMNLP-16). Austin, Texas, pages 1054–1059. find
28. Aleš Tamchyna, Chris Quirk, and Michel Galley. 2015. A discriminative model for semantics-to-string translation. In Proceedings of the 1st Workshop on Semantics-Driven Statistical Machine Translation (S2MT 2015). Beijing, China, pages 30– 36. find
29. Lucy Vanderwende, Arul Menezes, and Chris Quirk. 2015. An AMR parser for English, French, German, Spanish and Japanese and a new AMR-annotated corpus. In Proceedings of the 2015 Meeting of the North American chapter of the Association for Computational Linguistics (NAACL-15). pages 26–30. find
30. Chuan Wang, Nianwen Xue, and Sameer Pradhan. 2015. A transition-based algorithm for AMR parsing. In Proceedings of the 2015 Meeting of the North American chapter of the Association for Computational Linguistics (NAACL-15). pages 366–375. find
31. Dekai Wu. 1997. Stochastic inversion transduction grammars and bilingual parsing of parallel corpora. Computational linguistics 23(3):377–403. find our card
32. Jun Xie, Haitao Mi, and Qun Liu. 2011. A novel dependency-to-string model for statistical machine translation. In Conference on Empirical Methods in Natural Language Processing (EMNLP-11). Edinburgh, Scotland, UK., pages 216–226. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/song-2017-amr-text-generation-synchronous-node/