Identifying collocations in a text (e.g., break record) and correctly translating them (battre record vs. *casser record) represent key issues in machine translation, notably because of their prevalence in language and their syntactic flexibility. This article describes a method for discovering translation equivalents for collocations from parallel corpora, aimed at increasing the lexical cover...

There is a certain consensus on some defining features of collocations (they are frequent, recurrent, conventional, institutionalized, etc.), but there is not much agreement on other characteristics, for example whether or not they constitute binary lexical relations, and — crucially— whether they are arbitrary, and must be stipulated, or should instead be deduced or inferred. I will argue that...

Exemple : 1 ère itération : travail administratif 2 ème itération : responsabilité de travail-administratif À chaque itération, les collocations binaires (et ternaires pour les collocations prépositionnelles) sont sélectionnées avec une mesure statistique et l'ajout de paramètres [Roche et al., 2004]. Corpus étudiés :-Corpus de Ressources Humaines (société PerformanSe) – 3784 Ko (en français)-C...

Collocations in Japanese and Korean have been studied extensively based on statistical tools. The criteria for collocations in these languages, however, have not been fully established in the literature, and it is not obvious whether all statistically significant combinations of words could be regarded as collocations. In this article, we point out empirical problems in extracting collocations ...

This paper describes the compilation and subsequent analysis of a comparable corpus travel journalism in three languages (English, Italian, Polish). By means driven methodology, our study focuses on adjective/noun pairings, extracting list statistically significant collocations for each language observing differences similarities with those other two. Social Networks Analysis tolos are used to ...

This work presents an extensive comparison of language related problems for neural machine translation and phrase-based machine translation between German and English. The explored issues are related both to the language characteristics as well as to the machine translation process and, although related, are going beyond typical translation error classes. It is shown that themain advantage of t...

This paper mines collocations from two different web usage corpora, NTU proxy log and TTS search log. The precisions for NTU and TTS test data are 61.76% and 57.50%, respectively, by human judgment for 2% sampling of extracted collocations. For automatic evaluation, we submit extracted collocation to Google search engine, and the resulting page counts are used to compute the mutual information ...

The correct use of collocations is one of the most difficult tasks that the student faces when learning a second language, such that one of the goals of Computer Assisted Language Learning (CALL) is to develop programs that aim to identify collocation errors in learners’ writings and propose corrections. However, while statistical models currently used by most of these programs still manage to ...

The aim of the report is twofold. First, learning tools available in monolingual online dictionaries for learners English are described. Second, an evaluation usefulness provided. To meet aims present contribution, a survey was administered on 318 Polish students English. respondents, who participated lecture devoted to topic dictionaries, were instructed complete questionnaire. A mixed-questio...