Answering Questions of IAD Task using Reference Resolution of Follow-up Questions
نویسندگان
چکیده
In this paper, we will propose reference resolution method for follow-up questions in IAD task. In this method, our system classifies reference pattern of question sentences into three types and recognize antecedent using reference resolution algorithm for each type. In the evaluation, performance of our methods was not better results than our expectation. In Formal Run, our system got correct answers in 13 questions among 71 questions which our system got correct answer in Reference Run. However, according to the analysis of evaluation results, the main reason of low performance was lack of word information for recognition of referential elements. If our system can recognize word meanings correctly, some errors will not occur and reference resolution works well.
منابع مشابه
Answering Questions Of Information Access Dialogue (IAD) Task Using Ellipsis Handling Of Follow-Up Questions
In this paper, we propose ellipsis handling method for follow-up questions in Information Access Dialogue (IAD) task of NTCIR QAC3. In this method, our system classifies ellipsis patterns of question sentences into three types and recognizes elliptical elements using ellipsis handling algorithm for each type. In the evaluation using Formal Run and Reference Run data, there were several cases wh...
متن کاملAn Overview of NTCIR-5 QAC3
This paper provides an overview of NTCIR-5 QAC3 (Question Answering Challenge 3). QAC is a series of challenges for evaluating question answering technologies in Japanese. QAC3 follows the same course as QAC based on the success of the previous two workshops, with its task limited to that corresponding to QAC2 Subtask 3 aiming at the convergence of research resources for novel subjects. This ta...
متن کاملMultimodal follow - up questions to multimodal answers in a QA system
We are developing a dialogue manager (DM) for a multimodal interactive Question Answering (QA) system. Our QA system presents answers using text and pictures, and the user may pose follow-up questions using text or speech, while indicating screen elements with the mouse. We developed a corpus of multimodal follow-up questions for this system. This paper describes a detailed analysis of this cor...
متن کاملارزیابی منابع اطلاعاتی پزشکی مبتنی بر شواهد براساس میزان پاسخدهی به پرسشهای بالینی
Introduction: This study was to identify the best accessible electronic information resources for finding answers to clinical questions in Iranian National Medical Digital Library. Methods: 20 clinical questions were randomly selected from four areas: prevention and treatment, diagnosis, etiology and prognosis from American National Library of Medicine (NLM). The keywords were searched in info...
متن کاملEmploying Two Question Answering Systems in TREC 2005
In 2005, the TREC QA track had two separate tasks: the main task and the relationship task. To participate in TREC 2005 we employed two different QA systems. PowerAnswer-2 was used in the main task, whereas PALANTIR was used for the relationship questions. For the main task, new this year is the use of events as targets in addition to the nominal concepts used last year. Event targets ranged fr...
متن کامل