Abstract
In this paper, we describe an approach to analysis for spoken language translation that combines phrase-level grammar-based parsing and automatic domain action classification. The job of the analyzer is to transform utterances into a shallow semantic task-oriented interlingua representation. The goal of our hybrid approach is to provide accurate real-time analyses and to improve robustness and portability to new domains and languages.- Anthology ID:
- W03-3014
- Volume:
- Proceedings of the Eighth International Conference on Parsing Technologies
- Month:
- April
- Year:
- 2003
- Address:
- Nancy, France
- Venue:
- IWPT
- SIG:
- SIGPARSE
- Publisher:
- Note:
- Pages:
- 127–136
- Language:
- URL:
- https://aclanthology.org/W03-3014
- DOI:
- Cite (ACL):
- Chad Langley and Alon Lavie. 2003. Parsing Domain Actions with Phrase-Level Grammars and Memory-Based Learners. In Proceedings of the Eighth International Conference on Parsing Technologies, pages 127–136, Nancy, France.
- Cite (Informal):
- Parsing Domain Actions with Phrase-Level Grammars and Memory-Based Learners (Langley & Lavie, IWPT 2003)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/W03-3014.pdf