Extractive summarization of broadcast news

From HLT@INESC-ID

Revision as of 17:50, 2 November 2006 by David (talk | contribs)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.
Ricardo Daniel Ribeiro
Ricardo Daniel Ribeiro

Date

  • 15:30, November 03, 2006
  • 3rd floor meeting room

Speaker

Abstract

We present early results from our work on extractive summarization of broadcast news. The feature-based summarizer receives as input the automatic transcription of the news, already divided into stories, and produces as output a summary for each story. The main problems dealt with were sentence segmentation and scoring. Since summary evaluation requires hand-made summaries and/or human grading of the produced summaries, it is left as future work.