Paper: A Subcategorization Acquisition System for French Verbs

ACL ID P08-3010
Title A Subcategorization Acquisition System for French Verbs
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
Authors

This paper presents a system capable of auto- matically acquiring subcategorization frames (SCFs) for French verbs from the analysis of large corpora. We applied the system to a large newspaper corpus (consisting of 10 years of the French newspaper ’Le Monde’) and ac- quired subcategorization information for 3267 verbs. The system learned 286 SCF types for these verbs. From the analysis of 25 represen- tative verbs, we obtained 0.82 precision, 0.59 recall and 0.69 F-measure. These results are comparable with those reported in recent re- lated work.