Analyzing Methods for Improving Precision of Pivot Based Bilingual Dictionaries

Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pages 846–856, Edinburgh, Scotland, UK, July 27–31, 2011. c⃝2011 Association for Computational Linguistics Analyzing Methods for Improving Precision of Pivot Based Bilingual Dictionaries Xabier Saralegi, Iker Manterola, I˜naki San Vicente R&D Elhuyar Foundation Zelai haundi 3, Osinalde Industrialdea 20170 Usurbil, Basque Country {x.saralegi, i.manterola, i.sanvicente}@elhuyar.com Abstract An A-C bilingual dictionary can be inferred by merging A-B and B-C dictionaries using B as pivot. However, polysemous pivot words often produce wrong translation candidates. This paper analyzes two methods for pruning wrong candidates: one based on exploiting the structure of the source dictionaries, and the other based on distributional similarity computed from comparable corpora. As both methods depend exclusively on easily available resources, they are well suited to less resourced languages. We studied whether these two techniques complement each other given that they are based on different paradigms. We also researched combining them by looking for the best adequacy depending on various application scenarios. 1 Introduction Nobody doubts the usefulness and multiple applications of bilingual dictionaries: as the final product in lexicography, translation, language learning, etc. or as a basic resource in several fields such as Natural Language Processing (NLP) or Information Retrieval (IR), too. Unfortunately, only major languages have many bilingual dictionaries. Furthermore, construction by hand is a very tedious job. Therefore, less resourced languages (as well as less-common language pairs) could benefit from a method to reduce the costs of constructing bilingual dictionaries. With the growth of the web, resources like Wikipedia seem to be a good option to extract new bilingual lexicon (Erdmann et al., 2008), but the reality is that a dictionary is quite different from an encyclopedia. Wiktionary1 is a promising asset more oriented towards lexicography. However, the presence of less resourced languages in these kinds of resources is still relative -in Wikipedia, too-. Another way to create bilingual dictionaries is by using the most widespread languages (e.g., English, Spanish, French...) as a bridge between less resourced languages, since most languages have some bilingual dictionary to/from a major language. These pivot techniques allow new bilingual dictionaries to be built automatically. However, as the next section will show, it is no small task because translation between words is not a transitive relation at all. The presence of polysemous or ambiguous words in any of the dictionaries involved may produce wrong translation pairs. Several techniques have been proposed to deal with these ambiguity cases (Tanaka and Umemura, 1994; Shirai and Yamamoto, 2001; Bond et al., 2001; Paik et al., 2004; Kaji et al., 2008; Shezaf and Rappoport, 2010). However, each technique has different performance and properties producing dictionaries of certain characteristics, such as different levels of coverage of entries and/or translations. The importance of these characteristics depends on the context of use of the dictionary. For example, a small dictionary containing the most basic vocabulary and the corresponding most frequent translations can be adequate for some IR and NLP tasks, tourism, or initial stages of language learning. …

Content truncated to 500 words