A Language Model based Evaluator for Sentence Compression

We herein present a language-model-based evaluator for deletion-based sentence compression and view this task as a series of deletion-and-evaluation operations using the evaluator. More specifically, the evaluator is a syntactic neural language model that is first built by learning the syntactic and structural collocation among words. Subsequently, a series of trial-and-error deletion operations are conducted on the source sentences via a reinforcement learning framework to obtain the best target compression. An empirical study shows that the proposed model can effectively generate more readable compression, comparable or superior to several strong baselines. Furthermore, we introduce a 200-sentence test set for a large-scale dataset, setting a new baseline for the future research.

[1]  Yasemin Altun,et al.  Overcoming the Lack of Parallel Data in Sentence Compression , 2013, EMNLP.

[2]  Lejian Liao,et al.  Can Syntax Help? Improving an LSTM-based Sentence Compression Model for New Domains , 2017, ACL.

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

[4]  Dan Klein,et al.  Jointly Learning to Extract and Compress , 2011, ACL.

[5]  Jason Weston,et al.  A Neural Attention Model for Abstractive Sentence Summarization , 2015, EMNLP.

[6]  Yang Zhao,et al.  Gated Neural Network for Sentence Compression Using Linguistic Knowledge , 2017, NLDB.

[7]  Michael Strube,et al.  Dependency Tree Based Sentence Compression , 2008, INLG.

[8]  Joachim Bingel,et al.  Text Simplification as Tree Labeling , 2016, ACL.

[9]  Lukasz Kaiser,et al.  Sentence Compression by Deletion with LSTMs , 2015, EMNLP.

[10]  Björn W. Schuller,et al.  Contextual Bidirectional Long Short-Term Memory Recurrent Neural Network Language Models: A Generative Approach to Sentiment Analysis , 2017, EACL.

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

[12]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[13]  Chris Callison-Burch,et al.  Evaluating Sentence Compression: Pitfalls and Suggested Remedies , 2011, Monolingual@ACL.

[14]  Daniel Marcu,et al.  Statistics-Based Summarization - Step One: Sentence Compression , 2000, AAAI/IAAI.

[15]  Slav Petrov,et al.  Globally Normalized Transition-Based Neural Networks , 2016, ACL.

[16]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[17]  Mirella Lapata,et al.  Constraint-Based Sentence Compression: An Integer Programming Approach , 2006, ACL.

[18]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[19]  J. Clarke,et al.  Global inference for sentence compression : an integer linear programming approach , 2008, J. Artif. Intell. Res..

[20]  Alexander M. Rush,et al.  Abstractive Sentence Summarization with Attentive Recurrent Neural Networks , 2016, NAACL.

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