Statistical-based collocation extraction approaches suffer from (1) low precision rate because high co-occurrence bi-grams may be syntactically unrelated and are thus not true collocations; (2) low recall rate because some true collocations with low occurrences cannot be identified successfully by statistical-based models. To integrate both syntactic rules as well as semantic knowledge into a s...

This paper provides a specification of requirements for collocation extraction systems, taking as an example the extraction of noun + verb collocations from German texts. A hybrid approach to the extraction of habitual collocations and idioms is presented, aiming at a detailed description of collocations and their morphosyntax for natural language generation systems as well as to support learne...

In this paper we describe some interactions between collocations and automatic text categorization. First, we use the differents categories to extract strings (through collocations agglutinations) related to each categorie. Then we use these categories-specific strings to improve categorization. MOTS-CLÉS : collocations, catégorisation automatique de textes.

Abstract This paper examines how translation trainees deal with verb-noun terminological collocations when translating a legal text into their L2. The learner data is juxtaposed professional translations of the same and comparable non-translated documents. results indicate that large proportion renditions attested in reference corpora. There also relatively high convergence between learners’ ex...

In this paper, we describe an algorithm that employs syntactic and statistical analysis to extract bilingual collocations from a parallel corpus. The preferred syntactic patterns are obtained from idioms and collocations in a machine-readable dictionary. Phrases matching the patterns are extract from aligned sentences in a parallel corpus. Those phrases are subsequently matched up via cross-lin...

The main aim of the ET-10/?5 project, 'Collocations and the Lexicalisation of Semantic Operations '1, is to evaluate the use of Mel'~uk's analysis of collocations in terms of lexical functions 2, as an interlingun device in a machine translation system. In this poster we only point out the main design issues involved in encoding the essential parts of this analysis in an HPSG-style framework. O...

This paper presents a Natural Language Processing (NLP) approach to filter Named Entities (NE) from a list of collocation candidates. The NE are defined as the names of ’People’, ’Places’, ’Organizations’, ’Software’, ’Illnesses’, and so forth. The proposed method is based on statistical measures associated with Web resources to identify NE. Our method has three stages: (1) Building artificial ...

This paper reports on experiments in classifying the semantic role annotations assigned to prepositional phrases in both PENN TREEBANK (version II) and FRAMENET (version 0.75). In both cases, experiments are done to see how the prepositions can be classified given the dataset’s role inventory, using standard word-sense disambiguation features, such as the parts of speech of surrounding words, a...

Natural languages are full of collocations, recurrent combinations of words that co-occur more often than expected by chance and that correspond to arbitrary word usages. Recent work in lexicography indicates that collocations are pervasive in English; apparently, they are common in all types of writing, including both technical and nontechnical genres. Several approaches have been proposed to ...