Paper: A Generic Sentence Trimmer with CRFs

ACL ID P08-1035
Title A Generic Sentence Trimmer with CRFs
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2008
  • Tadashi Nomoto (National Institute of Japanese Literature, Tokyo Japan)

The paper presents a novel sentence trimmer in Japanese, which combines a non-statistical yet generic tree generation model and Con- ditional Random Fields (CRFs), to address improving the grammaticality of compres- sion while retaining its relevance. Experi- ments found that the present approach out- performs in grammaticality and in relevance a dependency-centric approach (Oguro et al., 2000; Morooka et al., 2004; Yamagata et al., 2006; Fukutomietal., 2007)‚ąítheonlylineof work in prior literature (on Japanese compres- sion) we are aware of that allows replication and permits a direct comparison.