Source-Language Entailment Modeling for Translating Unknown Terms

Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, pages 791–799, Suntec, Singapore, 2-7 August 2009. c⃝2009 ACL and AFNLP Source-Language Entailment Modeling for Translating Unknown Terms Shachar Mirkin§, Lucia Specia†, Nicola Cancedda†, Ido Dagan§, Marc Dymetman†, Idan Szpektor§ § Computer Science Department, Bar-Ilan University † Xerox Research Centre Europe {mirkins,dagan,szpekti}@cs.biu.ac.il {lucia.specia,nicola.cancedda,marc.dymetman}@xrce.xerox.com Abstract This paper addresses the task of handling unknown terms in SMT. We propose us- ing source-language monolingual models and resources to paraphrase the source text prior to translation. We further present a conceptual extension to prior work by al- lowing translations of entailed texts rather than paraphrases only. A method for performing this process efficiently is pre- sented and applied to some 2500 sentences with unknown terms. Our experiments show that the proposed approach substan- tially increases the number of properly translated texts. 1 Introduction Machine Translation systems frequently encounter terms they are not able to translate due to some missing knowledge. For instance, a Statistical Ma- chine Translation (SMT) system translating the sentence “Cisco filed a lawsuit against Apple for patent violation” may lack words like filed and lawsuit in its phrase table. The problem is espe- cially severe for languages for which parallel cor- pora are scarce, or in the common scenario when the SMT system is used to translate texts of a do- main different from the one it was trained on. A previously suggested solution (Callison- Burch et al., 2006) is to learn paraphrases of source terms from multilingual (parallel) corpora, and expand the phrase table with these para- phrases1. Such solutions could potentially yield a paraphrased sentence like “Cisco sued Apple for patent violation”, although their dependence on bilingual resources limits their utility. In this paper we propose an approach that con- sists in directly replacing unknown source terms, 1As common in the literature, we use the term para- phrases to refer to texts of equivalent meaning, of any length from single words (synonyms) up to complete sentences. using source-language resources and models in or- der to achieve two goals. The first goal is coverage increase. The avail- ability of bilingual corpora, from which para- phrases can be learnt, is in many cases limited. On the other hand, monolingual resources and methods for extracting paraphrases from monolin- gual corpora are more readily available. These include manually constructed resources, such as WordNet (Fellbaum, 1998), and automatic meth- ods for paraphrases acquisition, such as DIRT (Lin and Pantel, 2001). However, such resources have not been applied yet to the problem of substitut- ing unknown terms in SMT. We suggest that by using such monolingual resources we could pro- vide paraphrases for a larger number of texts with unknown terms, thus increasing the overall cover- age of the SMT system, i.e. the number of texts it properly translates. Even with larger paraphrase resources, we may encounter texts in which not all unknown terms are successfully handled through paraphrasing, which often results in poor translations (see Section 2.1). To …

Content truncated to 500 words