Using Conceptual Vectors to get Magn Collocations (and using contrastive properties to get their translations)

This paper presents a semi-automatic approach for extraction of collocations from corpora which uses the results of Conceptual Vectors as a semantic filter. First, this method estimates the ability of each co-occurrence to be a collocation, using a statistical measure based on the fact that it occurs more often than by chance. Then the results are automatically filtered (with conceptual vectors) to retain only one given semantic kind of collocations. Finally we perform a new filtering based on manually entered data. Our evaluation on monolingual and bilingual experiments shows the interest to combine automatic extraction and manual intervention to extract collocations (to fill multilingual lexical databases). It proves especially that the use of conceptual vectors to filter the candidates allows us to increase the precision noticeably