Hebrew Morphological Preprocessing for Statistical Machine Translation

What it is about

The authors compare ways of splitting Hebrew words into tokens before Hebrew-to-English statistical translation with Moses, on a training set of about 64,000 sentences. Four regular-expression schemes split off more clitics at each level: S1 the conjunction and relativizer, S2 the prepositions, S3 the article, S4 the pronominal enclitics. Two other methods are compared: Morfessor, an unsupervised segmenter that knows no Hebrew, and HTAG, a morphological analyser with a context-sensitive tagger. On the blind test set, the untokenised baseline scores 19.31 BLEU. The best regular-expression scheme (S2) scores 21.69, Morfessor 22.25 and HTAG 22.79. Out-of-vocabulary tokens fall from 1311 to 556 with HTAG and to 48 with Morfessor. Morfessor's low OOV count comes from over-segmenting: it leaves about 82% of words whole and splits the rest aggressively. In the analysed OOV sample, 39% of cases had no clitic, 47% one and 14% two.

Ideas

• I1. Define the segmentation output as named, nested schemes (S1 to S4), and report for each the token inflation over the unsegmented input and the share of words left unchanged, as their Table 2 does. Use the same report for every segmenter Mova tests.
• I2. Clitic order is strict: conjunction, relativizer, preposition, article, base word, pronominal clitic. Encode it as an ordered check in the segmenter, so a split that breaks the order is rejected. Their listed exceptions (prepositions before the relativizer, such as m+š+) are a short list to test.
• I3. Use Morfessor as a negative control: a segmenter that scores well on OOV counts but over-segments and hurts the score is exactly what a measurement must catch. Report OOV counts and the downstream score together, never one alone.

For Mova

I1 and I3 go into the evaluation of tools/hbo. I2 goes into the segmenter tables of tools/hbo (pre, lex) and into Prepositions, prefixes, conjunctions and particles.

Topics: Machine translation

Cite

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

@inproceedings{singh2012hebrew,
  title = {{Hebrew Morphological Preprocessing for Statistical Machine Translation}},
  author = {Singh, Nimesh and Habash, Nizar},
  booktitle = {Proceedings of the 16th Annual Conference of the European Association for Machine Translation},
  year = {2012},
  url = {https://aclanthology.org/2012.eamt-1.8/}
}

References

30 references, 3 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Adler, Meni. 2009. Hebrew Morphological Disambiguation: An Unsupervised Stochastic Word-based Approach. Ph.D. thesis, Ben Gurion University. find
2. Al-Haj, Hassan and Alon Lavie. 2012. The impact of Arabic morphological segmentation on broad-coverage English-to-Arabic statistical machine translation. Machine Translation, 26:3–24. find
3. Banerjee, Satanjeev and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72, Ann Arbor, Michigan. find our card
4. Creutz, Mathias and Krista Lagus. 2007. Unsupervised models for morpheme segmentation and morphology learning. ACM Trans. Speech Lang. Process., 4:3:1– 3:34. find
5. Denkowski, Michael and Alon Lavie. 2010. Extending the meteor machine translation evaluation metric to the phrase level. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 250–253, Los Angeles, California. find
6. Doddington, George. 2002. Automatic Evaluation of Machine Translation Quality Using N-gram Co-Occurrence Statistics. In Human Language Technology, pages 128–132, San Diego. find
7. Dyer, Christopher, Smaranda Muresan, and Philip Resnik. 2008. Generalizing Word Lattice Translation. In Proceedings of ACL-08: HLT, Columbus, Ohio. find
8. El Kholy, Ahmed and Nizar Habash. 2012a. Orthographic and morphological processing for English– Arabic statistical machine translation. Machine Translation, 26:25–45. find
9. El Kholy, Ahmed and Nizar Habash. 2012b. Translate, Predict or Generate: Modeling Rich Morphology in Statistical Machine Translation. In Proceedings of EAMT 2012, Trento, Italy. find
10. Fishel, Mark and Harri Kirik. 2010. Linguistically motivated unsupervised segmentation for machine translation. In Proceedings of the seventh International Conference on Language Resources and Evaluation (LREC), Valletta, Malta. Goldwater, Sharon and David McClosky. Improving Statistical MT Through Morphological Analysis. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 676–683, Vancouver, Canada. find
11. Graff, David and Christopher Cieri. 2003. English Gigaword, LDC Catalog No.: LDC2003T05. Linguistic Data Consortium, University of Pennsylvania. find
12. Habash, Nizar and Fatiha Sadat. 2006. Arabic preprocessing schemes for statistical machine translation. In Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers, NAACL-Short ’06, pages 49–52, Stroudsburg, PA. find
13. Habash, Nizar. 2008. Four Techniques for Online Handling of Out-of-Vocabulary Words in Arabic-English Statistical Machine Translation. In Proceedings of ACL-08: HLT, Short Papers, pages 57–60, Columbus, Ohio. find
14. Habash, Nizar. 2010. Introduction to Arabic Natural Language Processing. Morgan & Claypool Publishers. find
15. Itai, Alon and Shuly Wintner. 2008. Language resources for Hebrew. Language Resources and Evaluation, 42:75–98. find
16. Koehn, P. and K. Knight. 2003. Empirical methods for compound splitting. In Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics-Volume 1, pages 187– 193. find
17. Koehn, Philipp, Hieu Hoang, Alexandra Birch, Christopher Callison-Burch, Marcello Federico, Nicola Bertoldi, Brooke Cowan, Wade Shen, Christine Moran, Richard Zens, Christopher Dyer, Ondrej Bojar, Alexandra Constantin, and Evan Herbst. 2007. Moses: open source toolkit for statistical machine translation. In Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics Companion Volume Proceedings of the Demo and Poster Sessions, pages 177–180, Prague, Czech Republic. find
18. Koehn, Philipp. 2004. Statistical Significance Tests for Machine Translation Evaluation. In Proceedings of the Empirical Methods in Natural Language Processing Conference (EMNLP’04), Barcelona, Spain. find
19. Lavie, A., S. Wintner, Y. Eytani, E. Peterson, and K. Probst. 2004. Rapid prototyping of a transfer-based Hebrew-to-English machine translation system. In 10th International Conference on Theoretical and Methodological Issues in Machine Translation (TMI). find our card
20. Lee, Y.S. 2004. Morphological analysis for statistical machine translation. In Proceedings of HLT-NAACL 2004: Short Papers, pages 57–60. find
21. Lembersky, Gennadi, Noam Ordan, and Shuly Wintner. 2011. Language Models for Machine Translation: Original vs. Translated Texts. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pages 363–374, Edinburgh, 2005. Scotland, UK. find
22. Nießen, Sonja and Hermann Ney. 2004. Statistical Machine Translation with Scarce Resources using Morpho-syntactic Information. Computational Linguistics, 30(2). find
23. Och, Franz Josef. 2003. Minimum Error Rate Training for Statistical Machine Translation. In Proceedings of the 41st Annual Conference of the Association for Computational Linguistics, pages 160–167, Sapporo, Japan. find
24. Papineni, Kishore, 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, pages 311–318, Philadelphia, PA. find our card
25. Popović, Maja and Hermann Ney. 2004. Towards the Use of Word Stems and Suffixes for Statistical Machine Translation. In Proceedings of the 4th International Conference on Language Resources and Evaluation (LREC), pages 1585–1588, Lisbon, Portugal. find
26. Rosti, Antti-Veikko, Necip Fazil Ayan, Bing Xiang, Spyros Matsoukas, Richard Schwartz, and Bonnie Dorr. 2007. Combining outputs from multiple machine translation systems. In Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proceedings of the Main Conference, pages 228–235, Rochester, New York. find
27. Shilon, Reshef, Nizar Habash, Alon Lavie, and Shuly Wintner. 2012. Machine translation between Hebrew and Arabic. Machine Translation, 26:177–195. find
28. Snyder, Benjamin and Regina Barzilay. 2008. Unsupervised Multilingual Learning for Morphological Segmentation. In Proceedings of ACL-08: HLT, pages 737–745, Columbus, Ohio. find
29. Tsvetkov, Y. and S. Wintner. 2010. Automatic acquisition of parallel corpora from websites with dynamic content. In Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC’10), pages 3389–3392. find
30. Virpioja, Sami, Jaakko J. Vyrynen, Mathias Creutz, and Markus Sadeniemi. 2007. Morphology-aware statistical machine translation based on morphs induced in an unsupervised manner. In Proceedings of Machine Translation Summit, Copenhagen, Denmark. find

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/lingbulk-2012-singh-hebrew-morphological-preprocessing-statistical-machine/