Academic Commons

Presentations (Communicative Events)

A Skip-Chain Conditional Random Field for Ranking Meeting Utterances by Importance

Galley, Michel

We describe a probabilistic approach to content selection for meeting summarization. We use skipchain Conditional Random Fields (CRF) to model non-local pragmatic dependencies between paired utterances such as Question-Answer that typically appear together in summaries, and show that these models outperform linear-chain CRFs and Bayesian models in the task. We also discuss different approaches for ranking all utterances in a sequence using CRFs. Our best performing system achieves 91.3% of human performance when evaluated with the Pyramid evaluation metric, which represents a 3.9% absolute increase compared to our most competitive non-sequential classifier.


More About This Work

Academic Units
Computer Science
Proceedings of EMNLP
Published Here
June 30, 2013
Academic Commons provides global access to research and scholarship produced at Columbia University, Barnard College, Teachers College, Union Theological Seminary and Jewish Theological Seminary. Academic Commons is managed by the Columbia University Libraries.