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

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

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.

[1] D. Maynard. Placement of topic changes in conversation , 1980 .

[2] Gökhan Tür,et al. Integrating Prosodic and Lexical Cues for Automatic Topic Segmentation , 2001, CL.

[3] W. Levelt. Speaking: From Intention to Articulation , 1990 .

[4] Jan Renkema,et al. Discourse Studies: An Introductory Textbook , 1993 .

[5] Yiming Yang,et al. Topic Detection and Tracking Pilot Study Final Report , 1998 .

[6] Douglas E. Appelt,et al. FASTUS: A Finite-state Processor for Information Extraction from Real-world Text , 1993, IJCAI.

[7] Rebecca J. Passonneau,et al. Combining Multiple Knowledge Sources for Discourse Segmentation , 1995, ACL.

[8] Claire Cardie,et al. University of Massachusetts: description of the CIRCUS system as used for MUC-4 , 1992, MUC.

[9] David R. Traum,et al. Utterance Units in Spoken Dialogue , 1996, ECAI Workshop on Dialogue Processing in Spoken Language Systems.

[10] E. Schegloff,et al. A simplest systematics for the organization of turn-taking for conversation , 1974 .

[11] Michael Halliday,et al. Cohesion in English , 1976 .

[12] Claire Cardie,et al. Empirical Methods in Information Extraction , 1997, AI Mag..

[13] Douglas E. Appelt,et al. FASTUS: A Cascaded Finite-State Transducer for Extracting Information from Natural-Language Text , 1997, ArXiv.