Bilingual lexicon extraction from comparable corpora is constrained by the small amount of available data when dealing with specialized domains. This aspect penalizes the performance of distributionalbased approaches, which is closely related to the reliability of word’s cooccurrence counts extracted from comparable corpora. A solution to avoid this limitation is to associate external resources...

Two studies investigated how convergence between linguistic representations in Dutch-French bilinguals affects the centers and boundaries of lexical categories for common household objects. In Study 1, correlations between typicality ratings for roughly corresponding categories were higher for bilinguals in their two languages than for monolinguals in each language, indicating that bilingual pr...

Building bilingual lexica from non-parallel data is a longstanding natural language processing research problem that could benefit thousands of resource-scarce languages which lack parallel data. Recent advances of continuous word representations have opened up new possibilities for this task, e.g. by establishing cross-lingual mapping between word embeddings via a seed lexicon. The method is h...

PURPOSE This study examined lexical-semantic organization of bilingual children in their 2 languages and in relation to monolingual age-mates. METHOD Twelve Mandarin-English bilingual and 12 English monolingual children generated 3 associations to each of 36 words. Responses were coded as paradigmatic (dog-cat) or syntagmatic (dog-bark). RESULTS Within the bilingual group, word association ...

This paper considers the problem of unsupervised semantic lexicon acquisition. We introduce a fully automatic approach which exploits parallel corpora, relies on shallow text properties, and is relatively inexpensive. Given the English FrameNet lexicon, our method exploits word alignments to generate frame candidate lists for new languages, which are subsequently pruned automatically using a sm...

An approach to tile Transfer phase of a Machine Translat ion system is presented, where the bilingual lexicon plays an active role, guiding Transfer by means of executable descriptions of word senses. The means for lexical sense specification are, however, general enough and can in principle apply to other system arthitectures, e.g. in tile Generation phase if Transfer is intentionally kept min...

We present a bilingual LSA (bLSA) framework for translation lexicon adaptation. The idea is to apply marginal adaptation on a translation lexicon so that the lexicon marginals match to indomain marginals. In the framework of speech translation, the bLSA method transfers topic distributions from the source to the target side, such that the translation lexicon can be adapted before translation ba...

Neural Machine Translation (NMT) has become the new state-of-the-art in several language pairs. However, it remains a challenging problem how to integrate NMT with a bilingual dictionary which mainly contains words rarely or never seen in the bilingual training data. In this paper, we propose two methods to bridge NMT and the bilingual dictionaries. The core idea behind is to design novel model...

This paper describes an experiment combining several existing data resources (parallel corpora, valency lexicon, morphological taggers, bilingual dictionary etc.) and exploiting them in a task of building a valency lexicon for a related language (Russian) derived from a high quality manually created valency lexicon for Czech (Vallex) containing several thousands of verbs with very rich syntacti...

A method is presented for splitting compound words into their constituents based on cognate words in the other language of a parallel corpus. A minor extension to the method using a bilingual lexicon (which may be statistically derived from the corpus) allows the decompounding of words that do not have cognates in the other language. Further, the algorithm can produce, as a by-product, a mappin...