Translation Assistance by Translation of L1 Fragments in an L2 Context

Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, pages 871–880, Baltimore, Maryland, USA, June 23-25 2014. c⃝2014 Association for Computational Linguistics Translation Assistance by Translation of L1 Fragments in an L2 Context Maarten van Gompel & Antal van den Bosch Centre for Language Studies Radboud University Nijmegen proycon@anaproy.nl Abstract In this paper we present new research in translation assistance. We describe a sys- tem capable of translating native language (L1) fragments to foreign language (L2) fragments in an L2 context. Practical ap- plications of this research can be framed in the context of second language learning. The type of translation assistance system under investigation here encourages lan- guage learners to write in their target lan- guage while allowing them to fall back to their native language in case the correct word or expression is not known. These code switches are subsequently translated to L2 given the L2 context. We study the feasibility of exploiting cross-lingual context to obtain high-quality translation suggestions that improve over statistical language modelling and word-sense dis- ambiguation baselines. A classification- based approach is presented that is in- deed found to improve significantly over these baselines by making use of a contex- tual window spanning a small number of neighbouring words. 1 Introduction Whereas machine translation generally concerns the translation of whole sentences or texts from one language to the other, this study focusses on the translation of native language (henceforth L1) words and phrases, i.e. smaller fragments, in a foreign language (L2) context. Despite the ma- jor efforts and improvements, automatic transla- tion does not yet rival human-level quality. Vex- ing issues are morphology, word-order change and long-distance dependencies. Although there is a morpho-syntactic component in this research, our scope is more constrained; its focus is on the faith- ful preservation of meaning from L1 to L2, akin to the role of the translation model in Statistical Ma- chine Translation (SMT). The cross-lingual context in our research ques- tion may at first seem artificial, but its design ex- plicitly aims at applications related to computer- aided language learning (Laghos and Panayiotis, 2005; Levy, 1997) and computer-aided transla- tion (Barrachina et al., 2009). Currently, lan- guage learners need to refer to a bilingual dictio- nary when in doubt about a translation of a word or phrase. Yet, this problem arises in a context, not in isolation; the learner may have already trans- lated successfully a part of the text into L2 leading up to the problematic word or phrase. Dictionar- ies are not the best source to look up context; they may contain example usages, but remain biased to- wards single words or short expressions. The proposed application allows code switch- ing and produces context-sensitive suggestions as writing progresses. In this research we test the feasibility of the foundation of this idea.The fol- lowing examples serve to illustrate the idea and demonstrate what output the proposed translation assistance system would ideally produce. The parts in bold correspond to respectively the in- serted fragment …

Content truncated to 500 words