Sciweavers

EMNLP
2010

Better Punctuation Prediction with Dynamic Conditional Random Fields

13 years 8 months ago
Better Punctuation Prediction with Dynamic Conditional Random Fields
This paper focuses on the task of inserting punctuation symbols into transcribed conversational speech texts, without relying on prosodic cues. We investigate limitations associated with previous methods, and propose a novel approach based on dynamic conditional random fields. Different from previous work, our proposed approach is designed to jointly perform both sentence boundary and sentence type prediction, and punctuation prediction on speech utterances. We performed evaluations on a transcribed conversational speech domain consisting of both English and Chinese texts. Empirical results show that our method outperforms an approach based on linear-chain conditional random fields and other previous approaches.
Wei Lu, Hwee Tou Ng
Added 11 Feb 2011
Updated 11 Feb 2011
Type Journal
Year 2010
Where EMNLP
Authors Wei Lu, Hwee Tou Ng
Comments (0)