Abstract
We identify a set of prosodic cues for parsing conversational speech and show how such features can be effectively incorporated into a statistical parsing model. On the Switchboard corpus of conversational speech, the system achieves improved parse accuracy over a state-of-the-art system which uses only lexical and syntactic features. Since removal of edit regions is known to improve downstream parse accuracy, we explore alternatives for edit detection and show that PCFGs are not competitive with more specialized techniques.
Original language | English |
---|---|
Title of host publication | Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing |
Subtitle of host publication | Proceedings of the Conference |
Place of Publication | Stroudsburg, PA |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 233-240 |
Number of pages | 8 |
DOIs | |
Publication status | Published - Oct 2005 |
Externally published | Yes |
Event | Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT - Vancouver, BC, Canada Duration: 6 Oct 2005 → 8 Oct 2005 |
Other
Other | Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, HLT/EMNLP 2005, Co-located with the 2005 Document Understanding Conference, DUC and the 9th International Workshop on Parsing Technologies, IWPT |
---|---|
Country/Territory | Canada |
City | Vancouver, BC |
Period | 6/10/05 → 8/10/05 |