Improvement of accuracy of question-answering based on question reformulation
| Project/Area Number |
17500062
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Media informatics/Database
|
|---|
| Research Institution | National University Corporation Yokohama National University |
|---|
Principal Investigator |
MORI Tatsunori National university Corporation, Yokohama National University, Graduate School of Environment and Information Sciences, Professor, 大学院・環境情報研究院, 教授 (70212264)
|
|---|
| Project Period (FY) |
2005 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥3,500,000 (Direct Cost: ¥3,500,000)
Fiscal Year 2006: ¥1,400,000 (Direct Cost: ¥1,400,000)
Fiscal Year 2005: ¥2,100,000 (Direct Cost: ¥2,100,000)
|
|---|
| Keywords | Question-answering / List-type question-answering / Ranking-type question-answering / Distribution of answer scores / EM algorithm / Contextual question-answering / Cross-lingual question-answering / 分脈依頼型質問応答 |
|---|
| Research Abstract |
This research originally aimed at the improvement of accuracy of list-type question answering. The list-type question-answering is the task in which a system requested to enumerate all correct answers to a given question. In our proposed method, we utilize the distribution of the score that an existing question answering system gives to answer candidates. First we assume that the distribution is a mixture of two distributions, i.e., one of the correct answers and one of the incorrect answers. Second we also suppose that each of the two distributions is a normal distribution. Under these assumptions, we proposed a method to separate the correct answers from the mixture of the distributions by using the EM algorithm. On the other hand, the boundary of the two distributions may be occasionally indistinct because there is a possibility that the question-answering system fails to produce appropriate scores. In such a case, we perform a re-calculation of scores according to the co-occurrence
… More
of each answer candidate and the keywords of the question sentence in the knowledge source.
The experimental results show that the utilization of the score distribution is effective for the list-type question-answering. However, the re-calculation of scores based on the co-occurrence does not work effectively.
Therefore, we also investigated a method based on the above findings, that is, the degree of distinctness of the two distributions' boundaries indicates the appropriateness of answer candidates that are found by the system for a given question. We generalized the notion of "question reformulation" as follows. We generate a set of question candidates by applying several possible interpretations to the original question. In this situation, the question reformulation can be achieved by selecting appropriate question candidates and their answer candidates.
For example, when we applied the question reformulation to contextual question-answering, the accuracy of question answering may be improved. The notion also can be used for the improvement of accuracy of cross-lingual question answering. Less
|
Report
(3 results)
Research Products
(6 results)
