Abstract
This paper presents a method for guiding semantic parsers based on a statistical model. The parser is example driven, that is, it learns how to interpret a new utterance by looking at some examples. It is mainly predicated on the idea that similarities exist between contexts in which individual parsing actions take place. Those similarities are then used to compute the degree of certainty of a particular parse. The treatment of word order and the disambiguation of meanings can therefore be learned.- Anthology ID:
- 2002.jeptalnrecital-poster.4
- Volume:
- Actes de la 9ème conférence sur le Traitement Automatique des Langues Naturelles. Posters
- Month:
- June
- Year:
- 2002
- Address:
- Nancy, France
- Venue:
- JEP/TALN/RECITAL
- SIG:
- Publisher:
- ATALA
- Note:
- Pages:
- 338–343
- Language:
- URL:
- https://aclanthology.org/2002.jeptalnrecital-poster.4
- DOI:
- Cite (ACL):
- Michel Généreux. 2002. An Example-Based Semantic Parser for Natural Language. In Actes de la 9ème conférence sur le Traitement Automatique des Langues Naturelles. Posters, pages 338–343, Nancy, France. ATALA.
- Cite (Informal):
- An Example-Based Semantic Parser for Natural Language (Généreux, JEP/TALN/RECITAL 2002)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2002.jeptalnrecital-poster.4.pdf