Lexical-Based Alignment for Reconstruction of Structure in Parallel Texts
In this paper, we present an optimization algorithm for finding the best text alignment based on the lexical similarity and the results of its evaluation as compared with baseline methods (Gale and Church, relative position). For evaluation, we use fiction texts that represent non-trivial cases of alignment. Also, we present a new method for evaluation of the algorithms of parallel texts alignment, which consists in restoration of the structure of the text in one of the languages using the units of the lower level and the available structure of the text in the other language. For example, in case of paragraph level alignment, the sentences are used to constitute the restored paragraphs. The advantage of this method is that it does not depend on corpus data.
Unable to display preview. Download preview PDF.
- 1.Gale, W.A., Church, K.W.: A program for Aligning Sentences in Bilingual Corpora. In: Proceedings of the 29th Annual Meeting of the Association for Computational Linguistics, Berkeley, California (1991)Google Scholar
- 2.Gelbukh, A., Sidorov, G., Vera-Félix, J.Á.: Paragraph-Level Alignment of an English-Spanish Parallel Corpus of Fiction Texts using Bilingual Dictionaries. In: Sojka, P., Kopeček, I., Pala, K. (eds.) Text, Speech and Dialogue. LNCS (LNAI), vol. 4188, pp. 61–67. Springer, Heidelberg (2006)CrossRefGoogle Scholar
- 4.Langlais, Ph., Simard, M., Veronis, J.: Methods and practical issues in evaluation alignment techniques. In: Proceedings of Coling-ACL-98 (1998)Google Scholar
- 5.Moore, R.C.: Fast and Accurate Sentence Alignment of Bilingual Corpora. AMTA-2002, pp. 135–144 (2002)Google Scholar