NTCIR-4 QAC Experiments at Matsushita

Question Answering System Using Concept-Based Vector Space Model

This paper presents the architecture of the Concept-based Vector Space Model Question Answering System (CBVSM-QAS) developed at the Nagaoka University of Technology (NUT) and used in the 4-th NTCIR workshop Question Answering Challenge (QAC) evaluation. The CBVSM-QAS runs on the factual question, which is, correspond to the subtask-1 in the NTCIR-4’s QAC. One major peculiarity of this system is...

POSTECH Question-Answering Experiments at NTCIR4-QAC

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 ...

NTCIR Experiments at Matsushita: TMREC Task

NTT's CCLQA System for NTCIR-7 ACLIA

This paper describes our Complex Cross-Lingual Question Answering (CCLQA) system based on the technologies used in our past NTCIR systems for QAC and CLQA. We implemented a new rule-based English question analyzer to extract English query terms, which are translated into Japanese by translation dictionaries. For DEFINITION, BIOGRAPHY, and EVENT questions, we reused our definition module for QAC...

NTT DATA Question-Answering Experiment at the NTCIR-3 QAC

In this paper, we give an overview of our questionanswering system for the NTCIR-3 QAC. Our system is based on an information-retrieval technique and an information-extraction technique by pattern matching. The system has three main stages: question analysis, passage retrieval, and answer extraction. In the passage-retrieval stage, two types of retrieval method are applied sequentially to narro...