Zhang, Sen, Wang, Bin and Jones, Gareth J.F.ORCID: 0000-0003-2923-8365
(2007)
ICT-DCU question answering task at NTCIR-6.
In: 6th NTCIR Workshop on Research in Information Access Technologies - Information Retrieval, Question Answering and Cross-Lingual Information Access, 15-18 May 2007, Tokyo, Japan.
This paper describes details of our participation in the
NTCIR-6 Chinese-to-Chinese Question Answering task. We
use the “retrieval plus extraction approach” to get answers
for questions. We first split the documents into short passages, and then retrieve potentially relevant passages for a question, and finally extract named entity answers from the most relevant passages. For question type identification, we use simple heuristic rules which cover most questions. The Lemur toolkit was used with the okapi model for document retrieval. Results of our task submission are given and some preliminary conclusions drawn.
Metadata
Item Type:
Conference or Workshop Item (Paper)
Event Type:
Workshop
Refereed:
Yes
Uncontrolled Keywords:
NTCIR; Chinese-to-Chinese Question Answering; Information Retrieval; Information Extraction;