Beyond Utterance Extraction: Summary Recombination for Speech Summarization

Jérémy Trione, Benoit Favre, Frederic Bechet


This paper describes a template filling approach for creating conversation summaries. The templates are generated from generalized summary fragments from a training corpus. Necessary pieces of information for filling them are extracted automatically from the conversation transcripts given linguistic features, and drive the fragment selection process. The approach obtains ROUGE-2 scores of 0.08471 on the RATP-DECODA corpus, which represents a significant improvement over extractive baselines and hand-written templates.


DOI: 10.21437/Interspeech.2016-855

Cite as

Trione, J., Favre, B., Bechet, F. (2016) Beyond Utterance Extraction: Summary Recombination for Speech Summarization. Proc. Interspeech 2016, 680-684.

Bibtex
@inproceedings{Trione+2016,
author={Jérémy Trione and Benoit Favre and Frederic Bechet},
title={Beyond Utterance Extraction: Summary Recombination for Speech Summarization},
year=2016,
booktitle={Interspeech 2016},
doi={10.21437/Interspeech.2016-855},
url={http://dx.doi.org/10.21437/Interspeech.2016-855},
pages={680--684}
}