This paper presents a multi-view approach for term translation spotting, based on a bilingual lexicon and comparable corpora. We propose to study different levels of representation for a term: the context, the theme and the orthography. These three approaches are studied individually and combined in order to rank translation candidates. We focus our task on French-English medical terms. Experim...

Bilingual teaching has experienced rapid growth in the Spanish educational panorama and numerous university programmes have emerged with aim of training future CLIL (Content Language Integrated Learning) teachers. However, there is little research assessing level linguistic competence foreign languages teachers, especially those who are studying for a bilingual degree. Although this work part b...

Bilingual lexicon extraction is useful, especially for low-resource languages that can leverage from high-resource languages. The Uyghur language a derivative language, and its resources are scarce noisy. Moreover, it difficult to find bilingual resource utilize the linguistic knowledge of other large languages, such as Chinese or English. There little related research on unsupervised Chinese-U...

the spreading activation models of mental lexicon's structure have presented the lexicon in multiple layers (semantic- syntactic- phonological). each layer is a network of nodes which are associated by links. the nature of these links is different from layer to layer. the literature for english speakers has shown that in the phonological layer, phonological forms of words have been linked based...

In this paper, we present a computational approach to bilingual speakers’ non-native (L2) lexical-semantic representations. Specifically, based on detailed analyses of the error patterns shown in our previous simulation results ( Zhao and Li Int. J. Bilingual. Educ. Bilingual., 2010, 13, 505–524 ; Li, Bilingualism, 2013, 16, 288–303 ), aim at revealing underlying learning factors that may affec...

We report experimental results on automatic extraction of an English-Chinese translation lexicon, by statistical analysis of a large parallel corpus, using limited amounts of linguistic knowledge. To our knowledge, these are the rst empirical results of the kind between an Indo-Europeanand non-Indo-Europeanlanguage for any signiicantvocabulary and corpus size. The learned vocabulary size is abo...

Independent component analysis (ICA) is a statistical method used to discover hidden features from a set of measurements or observed data so that the sources are maximally independent. This paper reports the first results on using ICA for the task of bilingual lexicon extraction from comparable corpora. We introduce two representations of data using ICA. The first one is called global ICA (GICA...