NTT's Question Answering System for NTCIR QAC2

NTT DATA Question-Answering Experiment at the NTCIR-4 QAC2

Question Answering Challenge for Information Access Dialogue - Overview of NTCIR4 QAC2 Subtask

We describe an overview of Question Answering Challenge (QAC) 2 Subtask 3, a novel challenge for evaluating open-domain question answering technologies, at the NTCIR Workshop 4. In QAC2 Subtask 3, question answering systems are supposed to be used interactively to answer a series of related questions, whereas in the conventional setting, systems answer isolated questions one by one. Such an int...

Question Answering Challenge for Five Ranked Answers and List Answers - Overview of NTCIR4 QAC2 Subtask 1 and 2

In this paper we describe an evaluation of question answering task, Question Answering Challenge 2 (QAC2). This evaluation project was first carried out at the NTCIR Workshop 3 in October 2002. One objective of the QAC was to develop practical QA systems in a general domain by focusing on research relating to user interaction and information extraction. Our second objective was to develop an ev...

NTCIR-4 QAC Experiments at Matsushita

This paper investigates our experimental results for NTCIR-4 QAC2, the second attempt to evaluate the technology of Japanese question answering (QA). Our basic approach is a combination of information retrieval and named entity (NE) extraction based on pattern matching. The results show that the accuracy of NE extraction crucially affects the overall performance of our system. Additional experi...

GDQA: Graph Driven Question Answering System - NTCIR-4 QAC2 Experiments

This paper is a detailed presentation of a question answering system developed for NTCIR-4. Our question answering system, GDQA, employs both a new text retrieval algorithm that is specialized for QA and a new algorithm for sorting the answer candidates. Using our new algorithm for text retrieval, articles containing the answer for the question can be retrieved with high precision. Our algorith...