The impact of ASR on abstractive vs. extractive meeting summaries

In this paper we describe a complete abstractive summarizer for meeting conversations, and evaluate the usefulness of the automatically generated abstracts in a browsing task. We contrast these abstracts with extracts for use in a meeting browser and investigate the effects of manual versus ASR transcripts on both summary types.

[1]  Ehud Reiter,et al.  Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[2]  Karen Spärck Jones.  Automatic summarising: factors and directions , 1998, ArXiv.

[3]  Klaus Zechner,et al.  Automatic Summarization of Open-Domain Multiparty Dialogues in Diverse Genres , 2002, CL.

[4]  Anoop Gupta,et al.  Auto-summarization of audio-video presentations , 1999, MULTIMEDIA '99.

[5]  Peter Poller,et al.  Extrinsic summarization evaluation: A decision audit task , 2008, TSLP.

[6]  Jean Carletta,et al.  The AMI meeting corpus , 2005 .

[7]  Giuseppe Carenini,et al.  Interpretation and Transformation for Abstracting Conversations , 2010, HLT-NAACL.

[8]  Tilman Becker,et al.  Combining Multiple Information Layers for the Automatic Generation of Indicative Meeting Abstracts , 2007, ENLG.

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

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

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

[12]  Julia Hirschberg,et al.  From text to speech summarization , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

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