Models for Sentence Compression: A Comparison across Domains, Training Requirements and Evaluation Measures

Sentence compression is the task of producing a summary at the sentence level. This paper focuses on three aspects of this task which have not received detailed treatment in the literature: training requirements, scalability, and automatic evaluation. We provide a novel comparison between a supervised constituentbased and an weakly supervised wordbased compression algorithm and examine how these models port to different domains (written vs. spoken text). To achieve this, a human-authored compression corpus has been created and our study highlights potential problems with the automatically gathered compression corpora currently used. Finally, we assess whether automatic evaluation measures can be used to determine compression quality.

• Type: Conference
• Year: 2006
• Where: ACL
• Authors: James Clarke, Mirella Lapata
• Keywords: ACL 2006, ACL 2007, Automatic Evaluation, Sentence Compression, Supervised Wordbased Compression