NTT's QA Systems for NTCIR QAC-1
نویسندگان
چکیده
In this paper, we describe two Question Answering systems that participated in the NTCIR QAC task. The first system, SAIQA-Ii, follows a standard worddistance approach. This system was designed to output the top five candidates and participated in TASK-1. The second system, SAIQA-Is, employs a logic-based approach. This system was designed to output only the most likely candidates and participated in TASK-1 through TASK-3. The evaluation results showed that SAIQA-Ii’s word-distance approach was more suitable for TASK-1 than SAIQA-Is’s; however, SAIQAIs’s logic-based approach was promising in TASK-2 and TASK-3.
منابع مشابه
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...
متن کاملNTT's Question Answering System for NTCIR-6 QAC-4
NTCIR-6 QAC-4 organizers announced that there would be no restriction (such as factoid) on QAC4 questions, but they plan to include many ‘definition’ questions and ‘why’ questions. Therefore, we focused on these two question types. For ‘definition’ questions, we used a simple pattern-based approach. For ‘why’ questions, hand-crafted rules were used in previous work for answer candidate extracti...
متن کاملA Unified Approach to Japanese and English Question Answering
We present our unified approach to question answering in different languages and describe our experiments on the Japanese language NTCIR-3 Question Answering Challenge (QAC-1) tasks 1 and 2. The model we use for Japanese language question answering (QA) is identical to the one we have applied successfully on the English language TREC QA tasks, based on a novel statistical, non-linguistic and da...
متن کاملOki QA System for QAC-2
This note describes OKI QA system for QAC-2 of NTCIR4. Our system has three characteristics: dependency-matching based answer extraction, run-time tagging, and learning-based query type analyzer. The result of the experiment implies that dependency revision technique will occupy an important position.
متن کاملQuestion Answering Challenge (QAC-1): An Evaluation of Question Answering Task at NTCIRWorkshop 3
In this paper we describe a question answering task, called Question Answering Challenge (QAC), and its first evaluation (QAC1). This was carried out as a task of NTCIR Workshop 3 in October 2002. In QAC, we aimed to encourage the development of practical QA systems in a general domain and focus on research of user interaction and information extraction. Developments of evaluation method of que...
متن کامل