Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

11

NLPRS
2001
Springer

favoriteEmaildiscussreport

128views Natural Language Processing» more NLPRS 2001»

Topic Segmentation : A First Stage to Dialog-Based Information Extraction

13 years 9 months ago

Topic Segmentation : A First Stage to Dialog-Based Information Extraction

Download www.afnlp.org

We study the problem of topic segmentation of manually transcribed speech in order to facilitate information extraction from dialogs. Our approach is based on a combination of multi-source knowledge modeled by hidden Markov models. We experiment with diﬀerent combinations of linguistic-level cues on dialogs dealing with search and rescue missions. Results show the eﬀectiveness of multi-source knowledge.

Narjès Boufaden, Guy Lapalme, Yoshua Bengio

Real-time Traffic

Hidden Markov Models | Multi-source Knowledge | Natural Language Processing | NLPRS 2001 | Topic Segmentation |

claim paper

Related Content

» Using Robust Methods for Automatic Extraction of Buildings

» A Bayesian Approach to Video Object Segmentation via Merging 3D Watershed Volumes

» Improving a genetic algorithm segmentation by means of a fast edge detection technique

» Discovering group nonverbal conversational patterns with topics

» AGORA the Interactive Document Image Analysis Tool of the BVH Project

» Userdriven page layout analysis of historical printed books

» On the Detection of Melody Notes in Polyphonic Audio

Post Info
More Details (n/a)

Added	30 Jul 2010
Updated	30 Jul 2010
Type	Conference
Year	2001
Where	NLPRS
Authors	Narjès Boufaden, Guy Lapalme, Yoshua Bengio

Comments (0)