Paper: Key-concept extraction from French articles with KX

ACL ID W12-1102
Title Key-concept extraction from French articles with KX
Venue JEP-TALN-RECITAL 2012, Workshop DEFT 2012: DÉfi Fouille de Textes (DEFT 2012 Workshop: Text Mining Challenge)
Session
Year 2012
Authors

We present an adaptation for the French text mining challenge (DEFT 2012) of the KX system for multilingual unsupervised key-concept extraction. KX carries out the selection of a list of weighted keywords from a document by combining basic linguistic annotations with simple statistical measures. In order to adapt it to the French language, a French morphological analyzer (PoS-Tagger) has been added into the extraction pipeline, to derive lexical patterns. Moreover, parameters such as frequency thresholds for collocation extraction and indicators for key-concepts relevance have been calculated and set on the training documents. In the DEFT 2012 tasks, KX achieved good results (i.e. 0.27 F1 for Task 1 - with terminological list, and 0.19 F1 for Task 2) with a limited additional effort for do...