Construction and Evaluation of a Dialog System Based on Mapping Sentence Meanings to the Dialog Context
-
- NOGUCHI Yasuhiro
- Graduate School of Science and Engineering, Shizuoka University Faculty of Informatics, Shizuoka University
-
- IKEGAYA Yuki
- Yamaha Marine Co., Ltd.
-
- KOGURE Satoru
- Faculty of Informatics, Shizuoka University
-
- KONDO Makoto
- Faculty of Informatics, Shizuoka University
-
- ASOH Hideki
- Information Technology Research Institute, AIST
-
- KOBAYASHI Ichiro
- Faculty of Science, Ochanomizu University
-
- KONISHI Tatsuhiro
- Faculty of Informatics, Shizuoka University
-
- TAKAGI Akira
- NLP Research Laboratory
-
- ITOH Yukihiro
- Graduate School of Science and Technology, Shizuoka University, Faculty of Informatics, Shizuoka University
Bibliographic Information
- Other Title
-
- 文脈への意味の位置付けを用いた対話システムとその評価
- 文脈への意味の位置付けを用いた対話システムとその評価(<特集>言語,テキストの知能情報処理)
- ブンミャク エノ イミ ノ イチズケ オ モチイタ タイワ システム ト ソノ ヒョウカ
Search this article
Description
A natural language dialogue system should correctly interpret input sentences from the users and extract information essential for proper response. Since a variety of surface dependency structures may carry the same meaning, a natural language dialog system should be able to interpret such variety of expressions. Traditional semantic representations, however, take over the variety of surface dependency structures without interpreting them. Consequently, we cannot compare semantic expressions with different dependency structure. In addition, it is practically impossible to prepare interpreting rules particular to each possible input. In our previous studies, we proposed a framework for semantic representations which circumvents the problem. The framework enables us to compare semantic representations with different dependency structures without employing structure-specific rules. In this paper, we describe how to interpret a clause based on its semantic representation and show that the interpreting processes are applicable to the interpretation of multiple clauses and/or multiple sentences. We have constructed a dialogue system based on this framework and evaluated the system. As a result, we have confirmed that the system can make proper response and that the framework gives the system capacity to make proper response, as desired.
Journal
-
- Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
-
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 20 (5), 732-756, 2008
Japan Society for Fuzzy Theory and Intelligent Informatics
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390282680163313920
-
- NII Article ID
- 110006975645
-
- NII Book ID
- AA1181479X
-
- ISSN
- 18817203
- 13477986
-
- HANDLE
- 10083/33779
-
- NDL BIB ID
- 9685876
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
- IRDB
- NDL
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed