Abstract
This paper presents an analysis of named entity recognition and classification in spontaneous speech transcripts. We annotated a significant fraction of the Switchboard corpus with six named entity classes and investigated a battery of machine learning models that include lexical, syntactic, and semantic attributes. The best recognition and classification model obtains promising results, approaching within 5% a system evaluated on clean textual data.
| Original language | English (US) |
|---|---|
| Pages | 3433-3436 |
| Number of pages | 4 |
| State | Published - Dec 1 2005 |
| Externally published | Yes |
| Event | 9th European Conference on Speech Communication and Technology - Lisbon, Portugal Duration: Sep 4 2005 → Sep 8 2005 |
Other
| Other | 9th European Conference on Speech Communication and Technology |
|---|---|
| Country | Portugal |
| City | Lisbon |
| Period | 9/4/05 → 9/8/05 |
ASJC Scopus subject areas
- Engineering(all)
Fingerprint Dive into the research topics of 'Named entity recognition from spontaneous open-domain speech'. Together they form a unique fingerprint.
Cite this
Surdeanu, M., Turmo, J., & Comelles, E. (2005). Named entity recognition from spontaneous open-domain speech. 3433-3436. Paper presented at 9th European Conference on Speech Communication and Technology, Lisbon, Portugal.