著者

松尾 豊 安田 雪

出版者

人工知能学会

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.22, pp.531-541, 2007-11-01

被引用文献数

30 12

---

Our purpose here is to (1) investigate the structure of the personal networks developed on mixi, a Japanese social networking service (SNS), and (2) to consider the governing mechanism which guides participants of a SNS to form an aggregate network. Our findings are as follows:the clustering coefficient of the network is as high as 0.33 while the characteristic path lenght is as low as 5.5. A network among central users (over 300 edges) consist of two cliques, which seems to be very fragile. Community-affiliation network suggests there are several easy-entry communities which later lead users to more high-entry, unique-theme communities. The analysis on connectedness within a community reveals the importance of real-world interaction. Lastly, we depict a probable image of the entire ecology on mixi among users and communities, which contributes broadly to social systems on the Web.

著者

鈴木 宏昭

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.19, pp.145-153, 2004-11-01

被引用文献数

6 1

---

The dynamic constraint relaxation theory predicts crucial roles of the initial diversity and evaluation in creative problem-solving. We reported the experimental evidence supporting these predictions, using an insight problem. The experiments showed that the degrees of making different types of trials and the appropriate evaluation were closely related to individual differences in insight problem-solving, and that evaluation became more appropriate by making the problem-solving goal explicit. The review of the research in related fields showed that these experimental findings were in congruent with the evidence obtained from different types of creative activities.

著者

徳久 良子 寺嶌 立太

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 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.21, pp.133-142, 2006-11-01

参考文献数

16

被引用文献数

6 5 1

---

The performance of a non-task-oriented conversational dialogue system greatly depends on whether it can generate high involvement during conversation with users. In this paper, we clarify the types of utterances concerning involvement in human-human conversational dialogue. First, we define Dialogue Acts(DAs) and Rhetorical Relations(RRs), and propose a method for measuring ``Involvement''. Next, we show that the inter-annotator agreement on these tag schemes is quite high. Finally, we investigate the relationship between DAs/RRs and Involvement. We found that affective utterances and cooperative utterances are significant to generate high involvement in conversational dialogue.

著者

藤澤 瑞樹 齋藤 豪 奥村 学

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.19, pp.483-492, 2004-11-01

参考文献数

9

被引用文献数

3

---

Previous commentary systems generate commentaries only from the viewpoint of a commentator. However there are various viewpoints for comments, and such different viewpoints invoke various comments. The amount of information about a situation may differ between the viewpoints, and the understandings of the situation may also differ between them. In this paper, we propose a method to generate commentaries automatically so that users can easily understand situations by taking into account the different understandings of the situations between viewpoints. Our method is composed of two parts. The first is generation of comment candidates about the current situation, unexpected actions, intentions of players by using a game tree. The second is comment selection which chooses comments related to the prior one so that listeners can compare the situations from different viewpoints. Based on our approach, we implemented an experimental system that generates commentaries on mahjong games. We discuss the output of the system.

著者

吉田 光男 荒瀬 由紀

出版者

人工知能学会

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI

巻号頁・発行日

vol.30, no.1, pp.161-171, 2015-01

---

Query classification is an important technique for web search engines, allowing them to improve users' search experience. Specifically, query classification methods classify queries according to topical categories, such as celebrities and sports. Such category information is effective in improving web search results, online advertisements, and so on. Unlike previous studies, our research focuses on trend queries that have suddenly become popular and are extensively searched. Our aim is to classify such trend queries in a timely manner, i.e., classify the queries on the same day when they become popular, in order to provide a better search experience. To reduce the expensive manual annotation costs to train supervised learning methods, we focus on a label propagation method that belongs to the semi-supervised learning family. Specifically, the proposed method is based on our previous method that constructs a graph using a corpus, and propagates a small number of ground-truth categories of labeled queries in order to estimate the categories of unlabeled queries. We extend this method to cut ineffective edges to improve both classification accuracy and computational efficiency. Furthermore, we investigate in detail the effects of different corpora, i.e., web/blog/news search results, Tweets, and news pages, on the trend query classification task. Our experiments replicate the situation of an emerging trend query; the results show that web search results are the most effective for trend query classification, achieving a 50.1% F-score, which significantly outperforms the state-of-the-art method by 7.2 points. These results provide useful insights into selecting an appropriate dataset for query classification from the various types of data available.

著者

長谷川 禎彦 伊庭 斉志

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.22, pp.37-47, 2007-11-01

参考文献数

34

被引用文献数

1 4

---

Genetic Programming (GP) is a powerful optimization algorithm, which employs the crossover for genetic operation. Because the crossover operator in GP randomly selects sub-trees, the building blocks may be destroyed by the crossover. Recently, algorithms called PMBGPs (Probabilistic Model Building GP) based on probabilistic techniques have been proposed in order to improve the problem mentioned above. We propose a new PMBGP employing Bayesian network for generating new individuals with a special chromosome called <I>expanded parse tree</I>, which much reduces a number of possible symbols at each node. Although the large number of symbols gives rise to the large conditional probability table and requires a lot of samples to estimate the interactions among nodes, a use of the expanded parse tree overcomes these problems. Computational experiments on two subjects demonstrate that our new PMBGP is much superior to prior probabilistic models.

著者

桑原 教彰 桑原 和宏 安部 伸治 須佐見 憲史 安田 清

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.20, pp.396-405, 2005-11-01

参考文献数

22

被引用文献数

6 4

---

Providing good home-based care to people with dementia is becoming an important issue as the size of the elderly population increases. One of the main problems in providing such care is that it must be constantly provided without interruption, and this puts a great burden on caregivers, who are often family members. Networked Interaction Therapy is the name we call our methods designed to relieve the stress of people suffering from dementia as well as that of their family members. This therapy aims to provide a system that interacts with people with dementia by utilizing various engaging stimuli. One such stimulus is a reminiscence video created from old photo albums, which is a promising way to hold a dementia sufferer's attention for a long time. In this paper, we present an authoring tool to assist in the production of a reminiscence video by using photo annotations. We conducted interviews with several video creators on how they used photo annotations such as date, title and subject of photos when they produced the reminiscence videos. According to the creators' comments, we have defined an ontology for representing the creators' knowledge of how to add visual effects to a reminiscence video. Subsequently, we developed an authoring tool that automatically produces a reminiscence video from the annotated photos. Subjective evaluation of the quality of reminiscence videos produced with our tool indicates that they give impressions similar to those produced by creators using conventional video editing software. The effectiveness of presenting such a video to people with dementia is also discussed.

著者

岡田 将吾 賀 小淵 小島 量 長谷川 修

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.22, pp.493-507, 2007-11-01

被引用文献数

1

---

This paper presents an unsupervised approach of integrating speech and visual information without using any prepared data(training data). The approach enables a humanoid robot, Incremental Knowledge Robot 1 (IKR1), to learn words' meanings. The approach is different from most existing approaches in that the robot learns online from audio-visual input, rather than from stationary data provided in advance. In addition, the robot is capable of incremental learning, which is considered to be indispensable to lifelong learning. A noise-robust self-organized incremental neural network(SOINN) is developed to represent the topological structure of unsupervised online data. We are also developing an active learning mechanism, called ``desire for knowledge'', to let the robot select the object for which it possesses the least information for subsequent learning. Experimental results show that the approach raises the efficiency of the learning process. Based on audio and visual data, we construct a mental model for the robot, which forms a basis for constructing IKR1's inner world and builds a bridge connecting the learned concepts with current and past scenes.

著者

安村 禎明 武市 雅司 新田 克己

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.18, pp.212-220, 2003-11-01

被引用文献数

5 8

---

This paper introduces a support system for making presentation slides from a technical paper. This system provides functions that assign slides to each section and put objects on a slide. Inputs to this system are a technical paper as a TeX document, the number of slides that a user wants to make, and keywords of the paper. First, the system converts a paper from a TeX document into an XML document. The XML document can include information of a paper such as ID numbers and term weights. Next, the system calculates weights of terms in the document by the TF*IDF method. Based on the term weights, objects in the document such as sentences, figures and tables are weighted. Using the weights of the objects and slide composition templates, the system decides how many slides are assigned to each section. If a user does not like the assignment, she/he can reassign slides to the section using a presentation composition editor. Then, the system selects a layout for a slide considering the objects in the slide, and extracts objects arranged on the slide. The user can rearrange the objects on the slide using a slide editor. Finally, outputs of the system are generated as presentation slides in XHTML. From experimental results, we concluded our system is useful for making presentation slides.

著者

後藤 匡史 長木 悠太 鈴木 英之進

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 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.16, pp.193-201, 2001-11-01

参考文献数

13

---

This paper presents a novel decision-tree induction for a multi-objective data set, i.e. a data set with a multi-dimensional class. Inductive decision-tree learning is one of the frequently-used methods for a single-objective data set, i.e. a data set with a single-dimensional class. However, in a real data analysis, we usually have multiple objectives, and a classifier which explains them simultaneously would be useful. A conventional decision-tree inducer requires transformation of a multi-dimensional class into a singledimensional class, but such a transformation can considerably worsen both accuracy and readability. In order to circumvent this problem we propose a bloomy decision tree which deals with a multi-dimensional class without such transformations. A bloomy decision tree consists of a set of decision nodes each of which splits examples according to their attribute values, and a set of .ower nodes each of which decidesa dimension of the class for examples. A flower node appears not only at the fringe of a tree but also inside a tree. Our pruning is executed during tree construction, and evaluates each dimension of the class based on Cram&eacute;r&rsquo;s V. The proposed method has been implemented as D3-B (Decision tree in Bloom), and tested with eleven benchmark data sets in the machine learning community. The experiments showed that D3-B has higher accuracies in nine data sets than C4.5 and tied with it in the other two data sets. In terms of readability, D3-B has a smaller number of decision nodes in all data sets, and thus outperforms C4.5. Moreover, experts in agriculture evaluated bloomy decision trees, each of which is induced from an agricultural data set, and found them appropriate and interesting.

著者

藤本 和則 島津 光伸

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 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.17, pp.162-165, 2002-11-01

参考文献数

8

被引用文献数

3 3

---

This paper describes availability of personal Web-pages and a prototype development for Decision Support for Internet Users, called DSIU, which is an area of research for decision support by using information on the Internet. The availability of Web-pages concerns usage of formal pages, which are provided by companies and so on, and personal pages, which are provided by private persons. Web-pages are gathered by using an Internet search engine to determine destinations for travel and personal pages are confirmed to provide much subjective information than formal pages. The prototype development concerns a travel recommendation system, which is a kind of decision support systems. The prototype uses subjective and objective information on the Internet to select several destinations for users and to provide explanations the reason why the destinations are recommended. This paper also describes our perspective of DSIU researches.

著者

平 博司 福島 伸一 大澤 幸生 伊庭 斉志 石塚 満

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 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.17, pp.268-275, 2002-11-01

参考文献数

21

被引用文献数

2 1

---

Information on the World Wide Web(WWW) is increasing day by day because of its open characteristics. It becomes difficult for users to find useful information in this huge WWW information space. Even if a user can fortunately find useful pages, it is difficult for him/her to acquire all the aspects or a structured knowledge view regarding his/her query. &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;In this paper, we describe a system called &ldquo;AreaView2001&rdquo;, which presents an overall structured view of the queried area together with a set of useful Web pages explaining the area and its subareas. The style of the presentation is similar to book style, consisiting of chapters and sections. When extracting important keywords of the area from collected Web pages, the system employs the method of KeyGraph which can extract keywords of the main topics and underlying basis knowledge of a text document. &nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;AreaView2001 is particularly useful for those users that want to know unfamiliar areas, such as academic areas, since the area knowledge available in the WWW will be presented as a collection of useful Web pages sorted out according to the overall structure of the area. Although the area knowledge to be presented by the system is not so well structured as book chapters because of the full-automatic structuring, it can provide a variety of vivid knowledge not available in books. Some experimental evaluations are given to illustrate the effectiveness of the sysytem.

著者

熊本 忠彦 太田 公子

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.21, pp.310-318, 2006-11-01

参考文献数

12

被引用文献数

7 5

---

Impression-based music retrieval helps users in finding musical pieces that suit their preferences, feelings, or mental states from the huge volume of a music database. We have therefore developed an impression-based music retrieval system that enables this. Users are asked to select one or more pairs of impression words from the multiple pairs presented by the system and estimate each of the selected pairs on a seven-step scale in order to input their impressions into the system. For instance, if they want to locate musical pieces that will create a happy impression, they should check the radio button ``Happy'' in the impression scale, ``Very happy -- Happy -- A little happy -- Neutral -- A little sad -- Sad -- Very sad,'' where a pair of impression words with a seven-step scale is called an ``impression scale'' in this paper. The system would measure the distance between the impressions of every musical piece in a user-specified music database and the impressions inputted by the user, and determine candidate musical pieces to be presented as retrieval results. In this paper, we define the form of vectors that numerically express impressions of musical pieces, and propose a method of generating such a vector from a musical piece. The most significant attribute of this method is that it uses n-gram statistics of information on pitch, strength, and length of every tone in that musical piece as features extracted from it. We also present the results of evaluating the performance of the system.

著者

伊藤 寛隆 田中 敏光 杉江 昇

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.18, pp.161-164, 2003-11-01

参考文献数

9

---

In order to realize advanced man-machine interfaces, it is desired to develop a system that can infer the mental state of human users and then return appropriate responses. As the first step toward the above goal, we developed a system capable of inferring human tactics in a simple game played between the system and a human. We present a machine learning system that plays a color expectation game. The system infers the tactics of the opponent, and then decides the action based on the result. We employed a modified version of classifier system like XCS in order to design the system. In addition, three methods are proposed in order to accelerate the learning rate. They are a masking method, an iterative method, and tactics templates. The results of computer experiments confirmed that the proposed methods effectively accelerate the machine learning. The masking method and the iterative method are effective to a simple strategy that considers only a part of past information. However, study speed of these methods is not enough for the tactics that refers to a lot of past information. For the case, the tactics template was able to settle the study rapidly when the tactics is identified.

著者

松原 仁 田中 久美子 Frank Ian 田所 諭

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.17, pp.177-180, 2002-11-01

被引用文献数

4 2

---

We address the problem of information flow in disaster relief scenarios by presenting an architecture for generating natural language dialogue between large numbers of agents. This architecture is the first step towards real-time support systems for relief workers and their controllers. Our work demonstrates how natural generation techniques from the MIKE commentary system for RoboCup soccer can be carried over to that of RoboCup Rescue. Thanks to this background, the initial product of our research is a system that explains a RoboCup Rescue simulation not to the agents in the domain themselves but to a watching audience. This "commentary" is produced by recreating the actual dialogues most likely be occurring in the domain: walkie-talkie-conversations.

著者

前野 義晴 大澤 幸生

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.22, pp.389-396, 2007-11-01

被引用文献数

4 3

---

This paper addresses a new problem to infer an invisible fixer in an organization from communication (node discovery problem). Human-interactive annealing together with crystallization algorithm aims at inventing scenarios from the gap between prior understanding and observation. Four functions for ranking the relevance of the portion of observation, and two types of communication strength within an organization are studied. In the experiment, information relevant to identify an invisible fixer in an online decision-making environment is successfully retrieved.

著者

岩爪 道昭 小林 一郎 伊藤 紀子 高橋 祐介 藤城 浩子 菅野 道夫

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.17, pp.181-185, 2002-11-01

被引用文献数

4 4

---

The aim of this study is to provide all people, from small children to aged persons, with a computational environment for everyday language communication. In order to achieve this, we propose a framework for a language-based operating system. In this paper, we explain our approach to dealing with the meaning of language, the architecture of the language operating system and its components. In particular, we describe the notion of language protocol and its resource representation (i.e., semiotic base), compared to the other protocols and their resource representations. We argue that by processing meaning of language rather than processing information, we attempt to provide a more human-like computer system and an intelligent computational environment to all people.

著者

中嶋 宏 森島 泰則 山田 亮太 Scott Brave Heidy Maldonado Clifford Nass 川路 茂保

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.19, pp.184-196, 2004-11-01

被引用文献数

1 15

---

In this information society of today, it is often argued that it is necessary to create a new way of human-machine interaction. In this paper, an agent with social response capabilities has been developed to achieve this goal. There are two kinds of information that is exchanged by two entities: objective and functional information (e.g., facts, requests, states of matters, etc.) and subjective information (e.g., feelings, sense of relationship, etc.). Traditional interactive systems have been designed to handle the former kind of information. In contrast, in this study social agents handling the latter type of information are presented. The current study focuses on sociality of the agent from the view point of Media Equation theory. This article discusses the definition, importance, and benefits of social intelligence as agent technology and argues that social intelligence has a potential to enhance the user's perception of the system, which in turn can lead to improvements of the system's performance. In order to implement social intelligence in the agent, a mind model has been developed to render affective expressions and personality of the agent. The mind model has been implemented in a human-machine collaborative learning system. One differentiating feature of the collaborative learning system is that it has an agent that performs as a co-learner with which the user interacts during the learning session. The mind model controls the social behaviors of the agent, thus making it possible for the user to have more social interactions with the agent. The experiment with the system suggested that a greater degree of learning was achieved when the students worked with the co-learner agent and that the co-learner agent with the mind model that expressed emotions resulted in a more positive attitude toward the system.

著者

池ヶ谷 有希 野口 靖浩 小暮 悟 伊藤 敏彦 小西 達裕 近藤 真 麻生 英樹 高木 朗 伊東 幸宏

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.22, pp.291-310, 2007-11-01

被引用文献数

3

---

This paper describes how to perform syntactic parsing and semantic analysis in a dialog system. The paper especially deals with how to disambiguate potentially ambiguous sentences using the contextual information. Although syntactic parsing and semantic analysis are often studied independently of each other, correct parsing of a sentence often requires the semantic information on the input and/or the contextual information prior to the input. Accordingly, we merge syntactic parsing with semantic analysis, which enables syntactic parsing taking advantage of the semantic content of an input and its context. One of the biggest problems of semantic analysis is how to interpret dependency structures. We employ a framework for semantic representations that circumvents the problem. Within the framework, the meaning of any predicate is converted into a semantic representation which only permits a single type of predicate: an identifying predicate "aru". The semantic representations are expressed as sets of "attribute-value" pairs, and those semantic representations are stored in the context information. Our system disambiguates syntactic/semantic ambiguities of inputs referring to the attribute-value pairs in the context information. We have experimentally confirmed the effectiveness of our approach; specifically, the experiment confirmed high accuracy of parsing and correctness of generated semantic representations.

著者

松尾 豊 友部 博教 橋田 浩一 中島 秀之 石塚 満

出版者

The Japanese Society for Artificial Intelligence

雑誌

人工知能学会論文誌 = Transactions of the Japanese Society for Artificial Intelligence : AI (ISSN:13460714)

巻号頁・発行日

vol.20, pp.46-56, 2005-11-01

被引用文献数

31 28

---

Social relation plays an important role in a real community.