Abstract Across languages, words carve up the world of experience in different ways. For example, English lacks an equivalent to Chinese superordinate noun tiáowèipǐn, which is loosely translated as “ingredients used season food while cooking.” Do such differences matter? A conventional label may offer a uniquely effective way communicating. On other hand, lexical gaps be easily bridged by comp...

In this paper, we introduce the task of selecting compact lexicon from large, noisy gazetteers. This scenario arises often in practice, in particular spoken language understanding (SLU). We propose a simple and effective solution based on matrix decomposition techniques: canonical correlation analysis (CCA) and rank-revealing QR (RRQR) factorization. CCA is first used to derive low-dimensional ...

Previous work on bilingual lexicon extraction from comparable corpora aimed at finding a good representation for the usage patterns of source and target words and at comparing these patterns efficiently. In this paper, we try to work it out in another way: improving the quality of the comparable corpus from which the bilingual lexicon has to be extracted. To do so, we propose a measure of compa...

We present methods to control the lexicon size when learning a Combinatory Categorial Grammar semantic parser. Existing methods incrementally expand the lexicon by greedily adding entries, considering a single training datapoint at a time. We propose using corpus-level statistics for lexicon learning decisions. We introduce voting to globally consider adding entries to the lexicon, and pruning ...

There is always a lexicon in a language learner ’s mind, with the lexical factors be represented. This paper proposes a dual-mode system to present vocabulary in the lexicon with access to rules and exemplars, which aims at facilitating the process to the lexicon with accuracy, appropriateness and idiomaticity.

The paper begins with the development of Amazighe lexicons with large coverage formalization. The built electronic lexicons, named ‘NAmLex’, ‘VAmLex’ and ‘PAmLex’ which stand for ‘Noun Amazighe Lexicon’, ‘Verb Amazighe Lexicon’ and ‘Particles Amazighe Lexicon’, link inflectional, morphological, and syntacticsemantic information to the list of lemmas. Automated inflectional and derivational rout...