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 constituent-based and an weakly supervised word-based 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.

[1]  Srinivas Bangalore,et al.  Evaluation Metrics for Generation , 2000, INLG.

[2]  金田 重郎,et al.  C4.5: Programs for Machine Learning (書評) , 1995 .

[3]  Ryan T. McDonald.  Discriminative Sentence Compression with Soft Syntactic Evidence , 2006, EACL.

[4]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[5]  Yi Pan,et al.  Sentence Compression for Automated Subtitling: A Hybrid Approach , 2004, ACL 2004.

[6]  Ronald Rosenfeld,et al.  Statistical language modeling using the CMU-cambridge toolkit , 1997, EUROSPEECH.

[7]  Gregory Grefenstette.  Producing Intelligent Telegraphic Text Reduction to provide an Audio Scanning Service for the Blind , 1998 .

[8]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[9]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[10]  William H. Press,et al.  Book-Review - Numerical Recipes in Pascal - the Art of Scientific Computing , 1989 .

[11]  Ted Briscoe,et al.  Robust Accurate Statistical Annotation of General Text , 2002, LREC.

[12]  Akira Shimazu,et al.  Probabilistic Sentence Reduction Using Support Vector Machines , 2004, COLING.

[13]  Akira Shimazu,et al.  Example-based sentence reduction using the hidden markov model , 2004, TALIP.

[14]  Stefan Riezler,et al.  Statistical Sentence Condensation using Ambiguity Packing and Stochastic Disambiguation Methods for Lexical-Functional Grammar , 2003, NAACL.

[15]  Simon Corston-Oliver,et al.  Text compaction for display on very small screens , 2001 .

[16]  Casimir A. Kulikowski,et al.  Computer Systems That Learn: Classification and Prediction Methods from Statistics, Neural Nets, Machine Learning and Expert Systems , 1990 .

[17]  Hongyan Jing,et al.  Sentence Reduction for Automatic Text Summarization , 2000, ANLP.

[18]  Sadaoki Furui,et al.  Speech Summarization: An Approach through Word Extraction and a Method for Evaluation , 2004, IEICE Trans. Inf. Syst..

[19]  Eugene Charniak,et al.  Supervised and Unsupervised Learning for Sentence Compression , 2005, ACL.

[20]  Daniel Marcu,et al.  Summarization beyond sentence extraction: A probabilistic approach to sentence compression , 2002, Artif. Intell..

[21]  Eugene Charniak,et al.  A Maximum-Entropy-Inspired Parser , 2000, ANLP.