Advertisement

Improving Word Alignment Using Alignment of Deep Structures

  • David Mareček
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5729)

Abstract

In this paper, we describe differences between a classical word alignment on the surface (word-layer alignment) and an alignment of deep syntactic sentence representations (tectogrammatical alignment). The deep structures we use are dependency trees containing content (autosemantic) words as their nodes. Most of other functional words, such as prepositions, articles, and auxiliary verbs are hidden. We introduce an algorithm which aligns such trees using perceptron-based scoring function. For evaluation purposes, a set of parallel sentences was manually aligned. We show that using statistical word alignment (GIZA++) can improve the tectogrammatical alignment. Surprisingly, we also show that the tectogrammatical alignment can be then used to significantly improve the original word alignment.

Keywords

Machine Translation Content Word Statistical Machine Translation Sentence Pair Word Alignment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Och, F.J., Ney, H.: A Systematic Comparison of Various Statistical Alignment Models. Computational Linguistics 29(1), 19–51 (2003)CrossRefGoogle Scholar
  2. 2.
    Menezes, A., Richardson, S.D.: A best-first alignment algorithm for automatic extraction of transfer mappings from bilingual corpora. In: Proceedings of the workshop on Data-driven methods in machine translation, vol. 14, pp. 1–8 (2001)Google Scholar
  3. 3.
    Sgall, P.: Generativní popis jazyka a česká deklinace. Academia, Prague (1967)Google Scholar
  4. 4.
    Hajič, J., Hajičová, E., Panevová, J., Sgall, P., Pajas, P., Štěpánek, J., Havelka, J., Mikulová, M.: Prague Dependency Treebank 2.0. Linguistic Data Consortium, LDC Catalog No.: LDC2006T01, Philadelphia (2006)Google Scholar
  5. 5.
    Haruno, M., Yamazaki, T.: High-performance Bilingual Text Alignment Using Statistical and Dictionary Information. In: Proceedings of the 34th conference of the Association for Computational Linguistics, pp. 131–138 (1996)Google Scholar
  6. 6.
    Watanabe, H., Kurohashi, S., Aramaki, E.: In: Finding Translation Patterns from Paired Source and Target Dependency Structures, pp. 397–420. Kluwer Academic, Dordrecht (2003)Google Scholar
  7. 7.
    Cuřín, J., Čmejrek, M., Havelka, J., Hajič, J., Kuboň, V., Žabokrtský, Z.: Prague Czech-English Dependency Treebank, Version 1.0. Linguistics Data Consortium, Catalog No.: LDC2004T25 (2004)Google Scholar
  8. 8.
    Bojar, O., Prokopová, M.: Czech-English Word Alignment. In: Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC 2006), ELRA, May 2006, pp. 1236–1239 (2006)Google Scholar
  9. 9.
    Bojar, O., Janíček, M., Žabokrtský, Z., Češka, P., Beňa, P.: CzEng 0.7: Parallel Corpus with Community-Supplied Translations. In: Proceedings of the Sixth International Language Resources and Evaluation (LREC’08), Marrakech, Morocco, ELRA (May 2008)Google Scholar
  10. 10.
    Žabokrtský, Z., Ptáček, J., Pajas, P.: TectoMT: Highly Modular MT System with Tectogrammatics Used as Transfer Layer. In: Proceedings of the 3rd Workshop on Statistical Machine Translation, ACL (2008)Google Scholar
  11. 11.
    McDonald, R., Pereira, F., Ribarov, K., Hajič, J.: Non-Projective Dependency Parsing using Spanning Tree Algorithms. In: Proceedings of Human Langauge Technology Conference and Conference on Empirical Methods in Natural Language Processing (HTL/EMNLP), Vancouver, BC, Canada, pp. 523–530 (2005)Google Scholar
  12. 12.
    Brants, T.: TnT - A Statistical Part-of-Speech Tagger. In: Proceedings of the 6th Applied Natural Language Processing Conference, Seattle, pp. 224–231 (2000)Google Scholar
  13. 13.
    Collins, M.: Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms. In: Proceedings of EMNLP, vol. 10, pp. 1–8 (2002)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • David Mareček
    • 1
  1. 1.Institute of Formal and Applied LinguisticsCharles University in PragueCzech Republic

Personalised recommendations