Abstractive Meeting Summarization as a Markov Decision Process

The task of abstractive summarization is formulated as a Markov Decision Process. Value Iteration is used to determine the optimal policy for natural language generation. While the approach is general, in this work we apply the system to the problem of automatically summarizing meeting conversations. The generated abstracts are superior to generated extracts according to intrinsic measures.

[1]  Dilek Z. Hakkani-Tür,et al.  Leveraging sentence weights in a concept-based optimization framework for extractive meeting summarization , 2009, INTERSPEECH.

[2]  Giuseppe Carenini,et al.  Abstractive Meeting Summarization with Entailment and Fusion , 2013, ENLG.

[3]  Jean Carletta,et al.  Multimodal Signal Processing , 2012 .

[4]  Mark T. Maybury,et al.  Automatic Summarization , 2002, Computational Linguistics.

[5]  Giuseppe Carenini,et al.  Abstractive Summarization of Spoken and Written Conversations Based on Phrasal Queries , 2014, ACL.

[6]  Giuseppe Carenini,et al.  The impact of ASR on abstractive vs. extractive meeting summaries , 2010, INTERSPEECH.

[7]  Jean Carletta,et al.  The AMI Meeting Corpus: A Pre-announcement , 2005, MLMI.

[8]  Giuseppe Carenini,et al.  Using the Omega Index for Evaluating Abstractive Community Detection , 2012, EvalMetrics@NAACL-HLT.

[9]  Eduard H. Hovy,et al.  Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics , 2003, NAACL.

[10]  Giuseppe Carenini,et al.  Methods for mining and summarizing text conversations , 2011, SIGIR '12.

[11]  Kishore Papineni,et al.  Why Inverse Document Frequency? , 2001, NAACL.

[12]  Fei Liu,et al.  Towards Abstractive Speech Summarization: Exploring Unsupervised and Supervised Approaches for Spoken Utterance Compression , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[13]  Claire Cardie,et al.  Domain-Independent Abstract Generation for Focused Meeting Summarization , 2013, ACL.

[14]  Giuseppe Carenini,et al.  Generating and Validating Abstracts of Meeting Conversations: a User Study , 2010, INLG.

[15]  Steve Gregory,et al.  An Algorithm to Find Overlapping Community Structure in Networks , 2007, PKDD.

[16]  Michel Galley,et al.  A Skip-Chain Conditional Random Field for Ranking Meeting Utterances by Importance , 2006, EMNLP.

[17]  Dilek Z. Hakkani-Tür,et al.  A global optimization framework for meeting summarization , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.