著者
上田 博唯 小林 亮博 佐竹 純二 近間 正樹 佐藤 淳 木戸出正継
出版者
一般社団法人情報処理学会
雑誌
情報処理学会論文誌 (ISSN:18827764)
巻号頁・発行日
vol.47, no.1, pp.87-97, 2006-01-15
被引用文献数
10

ユビキタス環境における対話型ロボットインタフェースの対話戦略を提案する.近い将来,ユビキタス環境は多種多様なホームサービスをユーザに提供すると期待されている.しかし,サービスの複雑化・多機能化にともない,用意されたすべてのサービスをユーザが把握することは困難となる.そこで,この課題を解決するために,ユーザの状況理解を補助し,サービス実行のきっかけとなるユーザ発話を誘導することができる,連想しりとり型対話戦略を提案する.この対話戦略は,ユーザが何気なく発話したキーワードをもとに関連する知識をしりとり的にユーザに提供することで,サービスのきっかけとなる発話をユーザから誘導する.ロボットは木構造で表現された知識を持ち,関連のあるキーワードを連想する.音声対話システムを試作し,対話のみを行う評価実験と実際にユビキタス型住宅での生活実験の中での評価実験を行った結果,連想しりとり型対話戦略の正当性を確認することができた.This paper presents a new dialog-strategy for an interactive robot interface in home network (so-called ubiquitous environment). In this environment the users can receive more intelligent services provided by many networked appliances. However it becomes more difficult for users to understand the whole services. In this paper we propose the associative shiritori dialog strategy. An interactive robot continuously tries to obtain a keyword that triggers the service through the shiritori like word game the conversation with the user. In this dialog-strategy, the interactive robot has the tree-structured knowledge that consists of keywords that are associated with the real world and services. Using this tree-structured knowledge, the robot chooses a matched keyword in the user's previous talked sentence. Then the robot construct the next utterance by using the tree-structured knowledge. By this mechanism, the robot can obtain the user's needs while the user feels that he/she has a natural conversation with the robot. We developed an interactive robot dialog system to evaluate our proposed strategy. Through the experiment, the robot showed its ability to obtain proper key words that trigger the meaningful services.
著者
中村 善一 木戸出 正継
出版者
THE INSTITUTE OF SYSTEMS, CONTROL AND INFORMATION ENGINEERS (ISCIE)
雑誌
システム制御情報学会論文誌 (ISSN:13425668)
巻号頁・発行日
vol.22, no.1, pp.37-47, 2009 (Released:2011-03-03)
参考文献数
29
被引用文献数
1 1

This paper investigates writer verification using feature parameters based on the knowledge of document examiners, which are automatically extracted from handwritten kanji characters on a digitizing tablet. Criteria of feature selection using the evaluation measure that is obtained by modifying the measure of decidability, d-prime, is established and the criteria are applied to the evaluation measures that are calculated from learning samples. Then two classifiers based on the frequency distribution of deviations of the selected features are proposed and its design method using learning samples is showed. The effectiveness of the proposed method is evaluated by verification experiments with the database including skilled forgeries. The experimental results show that the proposed methods are effective in writer verification.
著者
小作 浩美 内山 将夫 井佐原 均 河野 恭之 木戸出 正継
出版者
一般社団法人 人工知能学会
雑誌
人工知能学会論文誌 (ISSN:13460714)
巻号頁・発行日
vol.19, no.4, pp.225-233, 2004 (Released:2004-05-07)
参考文献数
15
被引用文献数
3 4

We have been developed a support system to interactively search certain articles of users' interest on the World Wide Web (WWW) without their hesitating over query choices. Especially we have been implementing an effective application system to enable tourists to easily find special event information of their interest and to enjoy their own tours. This system also enables developers of each system to provide them with the means of easily constructing an initial database and automatically updating it. As events are generally held cyclically, we have assumed events or keywords related to the events will appear in each term. If we can extract keywords that appear cyclically in a corpus including date information, we can obtain event keywords easily. The system can extract event information using the event keywords as queries for WWW information retrieval systems, and update the database automatically. In this paper, we introduce our support system with a focus on a concept to extract event keywords and event information through the appearance of keywords periodically. We found our approach effective by some experiments.