The bilingual lexicon, back and forth: Electrophysiological signatures of translation asymmetry

The research to be reported on in this paper was originally motivated by the finding that about 70% of the mistakes made by university students when translating from their mother tongue (Dutch) into their foreign language (French) were lexical in nature (NIENHUIS et al. 1989). This was partially confinned in the investigation described in NIENHUIS et al. (1993). A closer look at the individual errors suggested that many problems were caused by words with more than one meaning which each require different translations in the target language. In the research reported on in this paper, we checked our fmdings in the light of what is known about the structure of the bilingual lexicon and about the ways bilinguals have access to the elements of their two languages. On the basis of the model of the bilingual lexicon presented by KROLL & Sholl (1992) an adapted model is proposed for the processing of lexical ambiguity. This leads to a tentative schema of the mental activities that language learners have to perfonn when they are translating from their mother tongue into a foreign language, The second part of the paper describes two experiments we have carried out in order to find empirical support for such a schema. The last section of the paper contains a discussion of the results obtained as well as the conclusions that can be drawn.

Download Full-text

A comparative study on translation units for bilingual lexicon extraction

10.3115/1118037.1118049 ◽

2001 ◽

Cited By ~ 1

Author(s):

Kaoru Yamamoto ◽

Yuji Matsumoto ◽

Mihoko Kitamura

Keyword(s):

Comparative Study ◽

Bilingual Lexicon

Download Full-text

End-to-end statistical machine translation with zero or small parallel texts

Natural Language Engineering ◽

10.1017/s1351324916000127 ◽

2016 ◽

Vol 22 (4) ◽

pp. 517-548 ◽

Cited By ~ 5

Author(s):

ANN IRVINE ◽

CHRIS CALLISON-BURCH

Keyword(s):

Detailed Analysis ◽

Machine Translation ◽

Statistical Machine Translation ◽

Parallel Corpora ◽

Low Resource ◽

Bilingual Lexicon ◽

Orthographic Similarity ◽

Discriminative Model ◽

End To End ◽

Parallel Texts

AbstractWe use bilingual lexicon induction techniques, which learn translations from monolingual texts in two languages, to build an end-to-end statistical machine translation (SMT) system without the use of any bilingual sentence-aligned parallel corpora. We present detailed analysis of the accuracy of bilingual lexicon induction, and show how a discriminative model can be used to combine various signals of translation equivalence (like contextual similarity, temporal similarity, orthographic similarity and topic similarity). Our discriminative model produces higher accuracy translations than previous bilingual lexicon induction techniques. We reuse these signals of translation equivalence as features on a phrase-based SMT system. These monolingually estimated features enhance low resource SMT systems in addition to allowing end-to-end machine translation without parallel corpora.

Download Full-text