We participated in the SENSEVAL-3 English lexical sample task and multilingual lexical sample task. We adopted a supervised learning approach with Support Vector Machines, using only the official training data provided. No other external resources were used. The knowledge sources used were partof-speech of neighboring words, single words in the surrounding context, local collocations, and synta...

Collocational competence is of critical importance to EFL learners’ language proficiency. Due limited research on L1 influence L2 development receptive and productive knowledge adjective + noun collocations, especially in the context Vietnam, this study an attempt address these gaps by investigating whether Vietnamese learners could recognize use congruent English collocations more accurately t...

Acquiring vocabulary has always been recognized as a significant and challenging part of language learning process. In this study, the researcher examined the extent to which form recall of target lexical items by learners of English as a foreign language (EFL) is affected by a) repetition and b) by the type of target item; single words versus collocations. The treatment consisted of non-commun...

Coxhead’s (2000) Academic Word List (AWL) has been frequently used in EAP classrooms and re-examined in light of various domain-specific corpora. Although well-received, the AWL has been criticized for ignoring the fact that words tend to show irregular distributions and be used in different ways across disciplines (Hyland and Tse, 2007). One such difference concerns collocations. Academic word...

The usefulness of a statistical approach suggested by Church and Hanks (1989) is evaluated for the extraction of verb-noun (V-N) collocations from German text corpora. Some motivations for the extraction of V-N collocations from corpora are given and a couple of differences concerning the German language are mentioned that have implications on the applicability of extraction methods developed f...

One of the hardest problems for knowledge extraction from machine readable textual sources is distinguishing entities and events that are part of the main story from those that are part of the narrative structure, hnportantly, however, reported sl)eech in newspaper articles explicitly links these two levels. In this paper, we illustrate what the lexical semantics of reporting verbs must incorpo...

Non-substitutability is a property of Multiword Expressions (MWEs) that often causes lexical rigidity and is relevant for most types of MWEs. Efficient identification of this property can result in the efficient identification of MWEs. In this work we propose using distributional semantics, in the form of word embeddings, to identify candidate substitutions for a candidate MWE and model its sub...

This paper describes new functionalities implemented in a terminological database (TDB) in order to allow efficient editing of and access to multilingual data. The functionalities are original in the sense that they allow users of the database to retrieve the equivalents not only of headwords, but also of semantically related terms (especially collocations) that appear within the articles. The ...