Capturing Translational Divergences with a Statistical Tree-to-Tree Aligner

What it is about

The paper aligns the non-terminal nodes of English and French constituency parses automatically, with a statistical tree-to-tree aligner. The aim is not to make the two trees look alike, but to mark where they diverge, so a parallel treebank can record translational divergences. The aligner links each node at most once and prefers a set of links that is exact rather than large. Against a manually aligned treebank, the aligner does well at phrase level (non-lexical links, precision about 0.81 to 0.84, recall about 0.75 to 0.80), but poorly on lexical links (precision about 0.51 to 0.52, recall about 0.74 to 0.76). On all links, it proposes 10.4 to 11.0 links per tree pair against 8.3 in the manual version. Translation tests with a data-oriented model give BLEU between 0.509 and 0.533, which is close to the manual 0.522, because the automatic alignments give more coverage. The authors conclude that tree alignment should favour precision and be combined with broad word and phrase alignments.

Ideas

• I1. Count links by type for the reader: report the precision and recall of the meta-world's links against a hand-checked set of verses, split into lexical and non-lexical, as the paper does. This gives open problem 1 a measure per author pair.
• I2. A precision-first merge rule: the paper's lesson is that low-precision lexical links hurt. Apply it to the concept merges in the lexicon (open problem 2): keep a merge only if its precision on held-out verses is above a set threshold, and fall back to the copy otherwise.
• I3. Prefer few, exact links for the reader and keep a broad fallback: use the reader's exact links for divergences, and the standard word-to-word table for everything else. Count how often each path is used, so the fallback share is visible.
• I4. Report the link count per verse for each author. A reader that makes 25 percent more links than a hand-checked set (as here) is adding noise that a residual will show.

For Mova

The code is tools/translate/src/meta.rs (the links and concepts) and tools/roundtrip (the reader's trees). The aligner is statistical and rule-free, which fits Mova's counts. The paper's lexical-link weakness matches open problem 2, so its precision-and-recall table is the right measure for a residual-driven lexicon.

Topics: Machine translation

Cite

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

@inproceedings{hearne2007capturing,
  title = {{Capturing Translational Divergences with a Statistical Tree-to-Tree Aligner}},
  author = {Hearne, Mary and Tinsley, John and Zhechev, Ventsislav and Way, Andy},
  booktitle = {Proceedings of the 11th Conference on Theoretical and Methodological Issues in Machine Translation of Natural Languages: Papers},
  year = {2007},
  url = {https://aclanthology.org/2007.tmi-papers.11/}
}

References

30 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An Automatic Metric for MT Evaluation with Im-http://www.ichec.ie/proved Correlation with Human Judgments. In Proceedings of Workshop on Intrinsic and Extrinsic Evaluation Measures for MT and/or Summarization at the 43th Annual Meeting of the Association of Computational Linguistics (ACL-05), pages 65–72, Ann Arbor, MI. ↗
2. Daniel M. Bikel. 2002. Design of a Multi-lingual, Parallel-processing Statistical Parsing Engine. In Proceedings of the 2nd International Conference on Human Language Technology Research, pages 24– 27, San Francisco, CA. find
3. Eugene Charniak. 2000. A Maximum-Entropy-Inspired Parser. In Proceedings of the 1st Conference on North American Chapter of the Association for Computational Linguistics, pages 132–139, Seattle, Washington. find
4. David Chiang. 2005. A Hierarchical Phrase-Based Model for Statistical Machine Translation. In Proceedings of the 43nd Annual Meeting of the Association for Computational Linguistics (ACL’05), pages 263–270, Ann Arbor, MI. find our card
5. Ilyas Cicekli and H. Altay Güvenir. 2003. Learning Translation Templates from Bilingual Translation Examples. In Michael Carl and Andy Way, editors, Recent Advances in Example-Based Machine Translation, pages 255–286. Kluwer Academic Publishers, Dordrecht, The Netherlands. find
6. George Doddington. 2002. Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics. In Human Language Technology: Notebook Proceedings, pages 128–132, San Diego, CA. find
7. Bonnie J. Dorr, Lisa Pearl, Rebecca Hwa, and Nizar Habash. 2002. DUSTer: A Method for Unravelling Cross-Language Divergences for Statistical Word-Level Alignment. In Machine Translation: From Research to Real Users. Proceedings of the 5th Conference of the Association for Machine Translation in the Americas (AMTA 2002), pages 31–43, Tiburon, CA. find
8. Bonnie J. Dorr. 1994. Machine translation divergences: a formal description and proposed solution. Computational Linguistics, 20(4):597–633. find our card
9. Anette Frank. 1999. LFG-based syntactic transfer from English to French with the Xerox Translation Environment. In Proceedings of the ESSLLI’99 Summer School, Utrecht, The Netherlands. find
10. 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. find our card
11. Mary Hearne and Andy Way. 2006. Disambiguation Strategies for Data-Oriented Translation. In Proceedings of the 11th Conference of the European Association for Machine Translation (EAMT-06), pages 59–68, Oslo, Norway. find
12. W. John Hutchins and Harold Somers. 1992. An Introduction to Machine Translation. Academic Press, London. find
13. Philipp Koehn, Franz Josef Och, and Daniel Marcu. 2003. Statistical Phrase-Based Translation. In Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology (NAACL ’03), pages 48–54, Edmonton, Canada. find
14. Philipp Koehn, Hieu Hoang, Alexandra Birch, Chris Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Chris Dyer, Ondrej Bojar, Alexandra Constantin, and Evan Herbst. 2007. Moses: Open source toolkit for statistical machine translation. In Annual Meeting of the Association for Computational Linguistics (ACL), demonstration session, pages 177–180, Prague, Czech Republic. find
15. Percy Liang, Ben Taskar, and Dan Klein. 2006. Alignment by Agreement. In Proceedings of the 2006 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology (NAACL ’06), pages 104–111, New York City, NY. find
16. Jeremy Lindop and Jun-ichi Tsujii. 1992. Complex Transfer in MT: A Survey of Examples. Technical Report 91-5, Centre for Computational Linguistics, UMIST, Manchester. find
17. Yanjun Ma, Nicolas Stroppa, and Andy Way. 2007. Bootstrapping Word-Alignment via Word Packing. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics (ACL’07), pages 304–311, Prague, Czech Republic. find
18. Daniel Marcu, Wei Wang, Abdessamad Echihabi, and Kevin Knight. 2006. SPMT: Statistical Machine Translation with Syntactified Target Language Phraases. In Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP-06), pages 44–52, Sydney, Australia. find
19. I. Dan Melamed. 1998. Annotation Style Guide for the Blinker Project. Technical Report 98-06, IRCS, University of Pennsylvania, Philadelphia, PA. find
20. I. Dan Melamed. 2004. Statistical Machine Translation by Parsing. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL’04), pages 653–660, Barcelona, Spain. find
21. Franz Josef Och and Hermann Ney. 2003. A Systematic Comparison of Various Statistical Alignment Models. Computational Linguistics, 29(1):19–51. find
22. 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, Philadelphia, PA. find our card
23. Yvonne Samuelsson and Martin Volk. 2006. Phrase Alignment in Parallel Treebanks. In Proceedings of the 7th Conference of the 5th Workshop on Treebanks and Linguistic Theories (TLT 2006), Prague, Czech Republic. find
24. Jörg Tiedemann. 2004. Word to Word Alignment Strategies. In Proceedings of the 20th International Conference on Computational Linguistics (COL-ING ’04), pages 212–218, Geneva, Switzerland. find
25. John Tinsley, Ventsislav Zhechev, Mary Hearne, and Andy Way. 2007. Robust Language Pair-Independent Sub-Tree Alignment. In MT Summit XI, Copenhagen, Denmark. find
26. Arturo Trujillo. 1999. Translation Engines. Springer, London. find
27. Martin Volk and Yvonne Samuelsson. 2004. Bootstrapping Parallel Treebanks. In Proceedings of the 7th Conference of the Workshop on Linguistically Interpreted Corpora (LINC) , pages 71–77, Geneva, Switzerland. find
28. Benjamin Wellington, Sonjia Waxmonsky, and I. Dan Melamed. 2006. Empirical Lower Bounds on the Complexity of Translational Equivalence. In Proceedings of the 44th annual conference of the Association for Computational Linguistics (ACL-06), pages 977–984, Sydney, Australia. find
29. Dekai Wu. 2000. Bracketing and aligning words and constituents in parallel text using Stochastic Inversion Transduction Grammars. In Jean Veronis, editor, Parallel Text Processing: Alignment and Use of Translation Corpora, pages 139–167. Kluwer Academic Publishers, Dordrecht, The Netherlands. find
30. Andreas Zollmann and Ashish Venugopal. 2006. Syntax Augmented Machine Translation via Chart Parsing. In Proceedings of the HLT-NAACL 2006 Workshop on Statistical Machine Translation, pages 138–141, New York City, NY. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/hearne-2007-capturing-translational-divergences-statistical-tree/