TY - GEN
T1 - Extracting answers to natural language questions from large-scale corpus
AU - Li, Peng
AU - Wang, Xiao Long
AU - Guan, Yi
AU - Zhao, Yu Ming
PY - 2005
Y1 - 2005
N2 - This paper provides a novel and tractable method for extracting exact textual answers from the returned documents that are retrieved by traditional IR system in large-scale collection of texts. In our approach, WordNet and Web information are employed to improve the performance as external auxiliary resources, then some NLP technologies are used to constitute the empirical answer ranking formula, such as POS tagging, Named Entity recognition, and parser etc. The method involves automatically ranking passages with System Similarity Model, automatically downloading related Web pages by means of Web crawler, and automatically mining answers with empirical formula from candidate answer sets. The series of experimental results show that the overall performance of our system is good and the structure of the system is reasonable.
AB - This paper provides a novel and tractable method for extracting exact textual answers from the returned documents that are retrieved by traditional IR system in large-scale collection of texts. In our approach, WordNet and Web information are employed to improve the performance as external auxiliary resources, then some NLP technologies are used to constitute the empirical answer ranking formula, such as POS tagging, Named Entity recognition, and parser etc. The method involves automatically ranking passages with System Similarity Model, automatically downloading related Web pages by means of Web crawler, and automatically mining answers with empirical formula from candidate answer sets. The series of experimental results show that the overall performance of our system is good and the structure of the system is reasonable.
UR - https://www.scopus.com/pages/publications/33847313618
U2 - 10.1109/NLPKE.2005.1598824
DO - 10.1109/NLPKE.2005.1598824
M3 - 会议稿件
AN - SCOPUS:33847313618
SN - 0780393619
SN - 9780780393615
T3 - Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05
SP - 690
EP - 694
BT - Proceedings of 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05
T2 - 2005 IEEE International Conference on Natural Language Processing and Knowledge Engineering, IEEE NLP-KE'05
Y2 - 30 October 2005 through 1 November 2005
ER -