Learning to Translate with Source and Target Syntax

What it is about

Tree-to-tree translation, with syntax on both sides, has often done worse than phrase-based systems. The paper studies why, and proposes a simpler method. Instead of forcing the two parse trees to match, it keeps the hierarchical phrase-based model (Hiero) and adds syntactic features to it: whether a span's source side and target side match syntactic categories, and how well the chosen structure fits both grammars. The grammar is extracted with "fuzzy" tree-to-tree rules, which allow many new non-terminal labels, and the features let the model learn when to rely on syntax and when to fall back to monotone phrase-based translation. On Chinese-English, the fuzzy extraction gives about 0.9 BLEU on the test set over a string-to-string baseline, with an exact tree-to-tree extraction below it. On Arabic-English, the gain is smaller. The paper also reports that the model learns more well-formed structures, and it shows the frequency of each rewrite on both sides.

Ideas

• I1. Syntax as soft features, not hard constraints: the paper moves the syntactic constraint from the formalism into scores. For the encoder in tools/translate/src/profile.rs, add a count of how often a chunk's category fits the meta-tree slot, as a score term, and let the residual say whether it helps.
• I2. Compare exact and fuzzy extraction: the paper finds that exact tree-to-tree rules are worse than fuzzy ones. For the lexicon, count the concept merges that a strict rule (same concept, same tag, same head) would allow, and compare with a fuzzy rule (same concept, tags may differ), on the same dev split.
• I3. Rewrite frequencies as a check: the paper tabulates the rewrites above 1 percent on each side. Do the same for the meta-world: the most frequent head-child patterns of each author, to see which author deltas (open problem 8) are real.
• I4. Control: the paper's model must learn to revert to monotone translation when syntax does not help. The translator should have the same option, and report how often the encoder falls back to the copy path per author.

For Mova

The code is tools/translate/src/profile.rs and tools/translate/src/meta.rs. The method is count-based features over a hierarchical model, which fits Mova. Its neural parts are absent, and its gains are small, so each feature must be judged by the residual of exact mode, not by BLEU.

Topics: Machine translation

Cite

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

@inproceedings{chiang2010learning,
  title = {{Learning to Translate with Source and Target Syntax}},
  author = {Chiang, David},
  booktitle = {Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics},
  year = {2010},
  url = {https://aclanthology.org/P10-1146/}
}

References

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

1. Vamshi Ambati and Alon Lavie. 2008. Improving syntax driven translation models by re-structuring divergent and non-isomorphic parse tree structures. In Proc. AMTA-2008 Student Research Workshop, pages 235–244. find
2. Yehoshua Bar-Hillel. 1953. A quasi-arithmetical notation for syntactic description. Language, 29(1):47–58. find
3. Stanley F. Chen and Joshua Goodman. 1998. An empirical study of smoothing techniques for language modeling. Technical Report TR-10-98, Harvard University Center for Research in Computing Technology. find
4. David Chiang, Wei Wang, and Kevin Knight. 2009. 11,001 new features for statistical machine translation. In Proc. find
5. David Chiang. 2005. A hierarchical phrase-based model for statistical machine translation. In Proc. ACL 2005, pages 263–270. find our card
6. David Chiang. 2007. Hierarchical phrase-based translation. Computational Linguistics, 33(2):201–228. find our card
7. Michael Collins. 1997. Three generative lexicalised models for statistical parsing. In Proc. ACL-EACL, pages 16–23. find
8. Koby Crammer and Yoram Singer. 2003. Ultraconservative online algorithms for multiclass problems. Journal of Machine Learning Research, 3:951–991. find
9. Jason Eisner. 2003. Learning non-isomorphic tree mappings for machine translation. In Proc. ACL 2003 Companion Volume, pages 205–208. find our card
10. Victoria Fossum, Kevin Knight, and Steven Abney. 2008. Using syntax to improve word alignment for syntax-based statistical machine translation. In Proc. Third Workshop on Statistical Machine Translation, pages 44–52. find
11. Alexander Fraser and Daniel Marcu. 2007. Getting the structure right for word alignment: LEAF. In Proc. EMNLP 2007, pages 51–60. find
12. Michel Galley, Mark Hopkins, Kevin Knight, and Daniel Marcu. 2004. What’s in a translation rule? In Proc. HLT-NAACL 2004, pages 273–280. find our card
13. 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 Proc. COLING-ACL 2006, pages 961–968. find our card
14. Mary Hearne and Andy Way. 2003. Seeing the wood for the trees: Data-Oriented Translation. In Proc. MT Summit IX, pages 165–172. find
15. Liang Huang, Kevin Knight, and Aravind Joshi. 2006. Statistical syntax-directed translation with extended domain of locality. In Proc. AMTA 2006, pages 65–73. find our card
16. Alon Lavie, Alok Parlikar, and Vamshi Ambati. 2008. Syntax-driven learning of sub-sentential translation equivalents and translation rules from parsed parallel corpora. In Proc. SSST-2, pages 87–95. find
17. Yang Liu, Qun Liu, and Shouxun Lin. 2006. Tree-to-string alignment template for statistical machine translation. In Proc. COLING-ACL 2006, pages 609–616. find our card
18. Yang Liu, Yajuan Lü, and Qun Liu. 2009. Improving tree-to-tree translation with packed forests. In Proc. ACL 2009, pages 558–566. find
19. I. Dan Melamed, Giorgio Satta, and Ben Wellington. 2004. Generalized multitext grammars. In Proc. ACL 2004, pages 661–668. find
20. Slav Petrov, Leon Barrett, Romain Thibaux, and Dan Klein. 2006. Learning accurate, compact, and interpretable tree annotation. In Proc. COLING-ACL 2006, pages 433–440. find our card
21. Arjen Poutsma. 2000. Data-Oriented Translation. In Proc. COLING 2000, pages 635–641. find
22. David Talbot and Thorsten Brants. 2008. Randomized language models via perfect hash functions. In Proc. ACL-08: HLT, pages 505–513. find
23. Ashish Venugopal, Andreas Zollmann, Noah A. Smith, and Stephan Vogel. 2009. Preference grammars: Softening syntactic constraints to improve statistical machine translation. In Proc. find
24. David J. Weir. 1988. Characterizing Mildly Context-Sensitive Grammar Formalisms. Ph.D. thesis, University of Pennsylvania. find
25. Benjamin Wellington, Sonjia Waxmonsky, and I. Dan Melamed. 2006. Empirical lower bounds on the complexity of translational equivalence. In Proc. COLING-ACL 2006, pages 977–984. find
26. Min Zhang, Hongfei Jiang, Aiti Aw, Haizhou Li, Chew Lim Tan, and Sheng Li. 2008. A tree sequence alignment-based tree-to-tree translation model. In Proc. ACL-08: HLT, pages 559–567. find
27. Andreas Zollmann and Ashish Venugopal. 2006. Syntax augmented machine translation via chart parsing. In Proc. Workshop on Statistical Machine Translation, pages 138–141. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/chiang-2010-learning-translate-source-target-syntax/