Parsing Conversational Speech Using Enhanced Segmentation

Abstract

The lack of sentence boundaries and presence of disfluencies pose difficulties for parsing conversational speech. This work investigates the effects of automatically detecting these phenomena on a probabilistic parser's performance. We demonstrate that a state-of-the-art segmenter, relative to a pause-based segmenter, gives more than 45% of the possible error reduction in parser performance, and that presentation of interruption points to the parser improves performance over using sentence boundaries alone. Parsing speech can be useful for a number of tasks, including information extraction and question answering from audio transcripts. However, parsing conversational speech presents a different set of challenges than parsing text: sentence boundaries are not well-defined, punctuation is absent, and disfluencies (edits and restarts) impact the structure of language.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2004
Accession Number
ADA457886

Entities

People

  • Ciprian Chelba
  • Jeremy G. Kahn
  • Mari Ostendorf

Organizations

  • University of Washington

Tags

Communities of Interest

  • Space

DTIC Thesaurus Topics

  • Applied Computer Science
  • Artificial Intelligence
  • Artificial Intelligence Computing
  • Automatic
  • Boundaries
  • Computer Science
  • Computer Vision
  • Detection
  • Detectors
  • Hidden Markov Models
  • Language
  • Markov Models
  • Models
  • Precision
  • Probability
  • Recognition
  • Word Recognition

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Computer Vision.
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • AI & ML - Machine Translation