A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
This paper describes our system and additional experimental results in NTCIR-4 QAC Task 1. The main components of our system are question classification, passage retrieval, and named entity extraction. Passage retrieval was performed by a density-based ranking method based on importance of query terms occurred in the passage. Question classification and Named entity extraction were designed by the rule-based approach that uses lexico-semantic patterns, in which the Kadokawa thesaurus is basicdblp:conf/ntcir/NaKL04 fatcat:wn5bs44nkneqfemm3zu377zisu