Paper: Trimming CFG Parse Trees For Sentence Compression Using Machine Learning Approaches

ACL ID P06-2109
Title Trimming CFG Parse Trees For Sentence Compression Using Machine Learning Approaches
Venue Annual Meeting of the Association of Computational Linguistics
Session Poster Session
Year 2006
Authors

Sentence compression is a task of creating a short grammatical sentence by removing extraneous words or phrases from an origi- nal sentence while preserving its meaning. Existing methods learn statistics on trim- ming context-free grammar (CFG) rules. However, these methods sometimes elim- inate the original meaning by incorrectly removing important parts of sentences, be- cause trimming probabilities only depend on parents’ and daughters’ non-terminals in applied CFG rules. We apply a maxi- mum entropy model to the above method. Our method can easily include various features, for example, other parts of a parse tree or words the sentences contain. We evaluated the method using manually compressed sentences and human judg- ments. We found that our method pro- duced more grammatical and...