Translating Collocations for Use in Bilingual Lexicons

Translating Collocations for Use in Bilingual Lexicons Frank Smadja and Kathleen McKeown Computer Science Department Columbia University New York, NY 10027 (smadja/kathy) @cs.columbia.edu ABSTRACT Collocations are notoriously difficult for non-native speakers to translate, primarily because they are opaque and can not be translated on a word by word basis. We describe a program named Champollion which, given a pair of parallel corpora in two different languages, automatically produces translations of an input list of collocations. Our goal is to provide a tool to compile bilingual lexical information above the word level in multiple languages and domains. The algo- rithm we use is based on statistical methods and produces p word translations of n word collocations in which n and p need not be the same; the collocations can be either flexible or fixed compounds. For example, Champollion translates "to make a decision," "employ- ment equity," and "stock market," respectively into: "prendre une decision," "tquit6 en mati~re d'emploi," and "bourse." Testing and evaluation of Champollion on one year's worth of the Hansards cor- pus yielded 300 collocations and their translations, evaluated at 77% accuracy. In this paper, we describe the statistical measures used, the algorithm, and the implementation of Champollion, presenting our results and evaluation. 1. Introduction Hieroglyphics remained undeciphered for centuries until the discov- ery of the Rosetta Stone in the beginning of the 19th century in Rosetta, Egypt. The Rosetta Stone is a tablet of black basalt contain- ing parallel inscriptions in three different writings; one in greek, and the two others in two different forms of ancient Egyptian writings • (demotic and hieroglyphics). Jean-Francois Champollion, a linguist and egyptologist, made the assumption that these inscriptions were parallel and managed after several years of research to decipher the hyerogliphic inscriptions. He used his work on the Rosetta Stone as a basis from which to produce the first comprehensive hyeroglyphics dictionary. In this paper, we describe a modem version of a similar approach: given a large corpus in two languages, our program, Champollion, produces translations of common word pairs and phrases which can form the basis for a bilingual lexicon. Our focus is on the use of statistical methods for the translation of multi-word expressions, such as collocations, which cannot consistently be translated on a word by word basis. Bilingual collocation dictionaries are currently unavailable even in languages such as French and English despite the fact that collocations have been recognized as one of the main obstacles to second language acquisition [ 15]. We developed a program, Champollion, which translates colloca- tions using an aligned parallel bilingual corpus, or database cor- pus, as a reference. It represents Champollion's knowledge of both languages. For a given source language collocation, Champollion uses statistical methods to incrementally construct the collocation translation, adding one word at a time. Champollion first identifies individual words in the target language which are highly correlated with the source collocation. Then, it identifies any pairs in this set of individual words which are highly correlated with the source col- …

Content truncated to 500 words