Generation of natural responses through syntactic patterns

Glenda B. Anaya, Leila Kosseim


Abstract
The goal of Question-Answering (QA) systems is to find short and factual answers to opendomain questions by searching a large collection of documents. The subject of this research is to formulate complete and natural answer-sentences to questions, given the short answer. The answer-sentences are meant to be self-sufficient; that is, they should contain enough context to be understood without needing the original question. Generating such sentences is important in question-answering as they can be used to enhance existing QA systems to provide answers to the user in a more natural way and to provide a pattern to actually extract the answer from the document collection.
Anthology ID:
2003.jeptalnrecital-poster.1
Volume:
Actes de la 10ème conférence sur le Traitement Automatique des Langues Naturelles. Posters
Month:
June
Year:
2003
Address:
Batz-sur-Mer, France
Venue:
JEP/TALN/RECITAL
SIG:
Publisher:
ATALA
Note:
Pages:
297–302
Language:
URL:
https://aclanthology.org/2003.jeptalnrecital-poster.1
DOI:
Bibkey:
Cite (ACL):
Glenda B. Anaya and Leila Kosseim. 2003. Generation of natural responses through syntactic patterns. In Actes de la 10ème conférence sur le Traitement Automatique des Langues Naturelles. Posters, pages 297–302, Batz-sur-Mer, France. ATALA.
Cite (Informal):
Generation of natural responses through syntactic patterns (B. Anaya & Kosseim, JEP/TALN/RECITAL 2003)
Copy Citation:
PDF:
https://aclanthology.org/2003.jeptalnrecital-poster.1.pdf