Reference Lists for the Evaluation of Term Extraction Tools

Elizaveta Loginova Clouet (1) , Anita Gojun (2) , Helena Blancafort (3) , Marie Guegan (3) , Tatiana Gornostay (4) , Ulrich Heid (2)

1 LS2N - équipe TALN - Traitement Automatique du Langage Naturel
2 IMS, University of Stuttgart
3 Syllabs
4 TILDE

In this paper, we discuss practical and methodological issues of the creation of reference term lists (RTLs) for the evaluation of mono- lingual and bilingual term candidate extraction from comparable corpora in the domains of wind energy and mobile technology. These reference term lists are intended to serve as a "gold standard" for the qualita- tive and quantitative evaluation of automatic term extraction tools. We present the preliminary results of the evaluation of the monolingual term extraction. Using the manually collected RTLs, we evaluated monolin- gual term candidate lists which are automatically extracted from the Spanish texts in the domain of wind energy.

Mots clés: terminology extraction; multilingual context; comparable corpora; reference lists; evaluation

Domaines: Traitement du texte et du document; Informatique et langage [cs.CL]

Elizaveta Loginova Clouet, Anita Gojun, Helena Blancafort, Marie Guegan, Tatiana Gornostay, et al.. Reference Lists for the Evaluation of Term Extraction Tools. Terminology and Knowledge Engineering Conference (TKE), Jun 2012, Madrid, Spain. http://www.oeg-upm.net/tke2012/proceedings. ⟨hal-00816566⟩