人工知能学会論文誌
Online ISSN : 1346-8030
Print ISSN : 1346-0714
ISSN-L : 1346-0714
早期公開論文
早期公開論文の8件中1~8を表示しています
  • 5 Star Open Dataの実現
    浅野 優, 小出 誠二, 岩山 真, 加藤 文彦, 小林 厳生, 美馬 正司, 大向 一輝, 武田 英明
    論文ID: LOD-27
    発行日: 2016/01/06
    [早期公開] 公開日: 2017/01/31
    ジャーナル フリー 早期公開
    We describe a procedure for constructing a website for publishing open data by focusing on the case of Open DATA METI, a website of the Ministry of Economy, Trade, and Industry. We developed two sites for publishing open data: a data catalog site and one for searching linked open data (LOD). The former allows users to find relevant data they want to use, and the latter allows them to utilize the found data by connecting them. To implement the data catalog site, we constructed a site tailored to the needs of the organization. Then we extracted a large amount of metadata from the individual open data and put it on the site. These activities would have taken a lot of time if we had used the existing methods, so we devised our own solutions for them. To implement the LOD searching site, we converted the data into LOD form in the Resource Description Framework (RDF). We focused on converting statistical data into tables, which are widely used. Regarding the conversion, there were several kinds of missing information that we needed to associate with the data in the tables. We created a template for incorporating the necessary information for LOD in the original table. The conversion into LOD was automatically done using the template.
  • Corentin Jouault, Kazuhisa Seta, Yuki Hayashi
    論文ID: LOD-F
    発行日: 2016/01/06
    [早期公開] 公開日: 2016/02/18
    ジャーナル フリー 早期公開
    The objective of this research is to use current linked open data (LOD) to generate questions automatically to support history learning. This paper tries to clarify the potential of LOD as a learning resource. By linking LOD to natural language documents, we created an open learning space where learners have access to machine understandable natural language information about many topics. The learning environment supports learners with content-dependent questions. In this paper, we describe the question generation method that creates natural language questions using LOD. The integrated data is combined to a history domain ontology and a history dependent question ontology to generate content-dependent questions. To prove whether the generated questions have a potential to support learning, a human expert conducted an evaluation comparing our automatically generated questions with questions generated manually. The results of the evaluation showed that the generated questions could cover more than 80% of the questions supporting knowledge acquisition generated by humans. In addition, we confirmed the automatically generated questions have a potential to reinforce learners' deep historical understanding.
  • 吉田 俊介, 久門 正人, 守 真太郎
    論文ID: 30-6_JWEIN-B
    発行日: 2015/11/01
    [早期公開] 公開日: 2016/01/28
    ジャーナル フリー 早期公開
    We define the swarm intelligence effect and obtain the condition for the emergence of it in an interactive game of restless multi-armed bandit where a player competes with multiple agents. Each arm in the bandit has a payoff which change with probability pc per round. Agents and a player choose one from three options: (1) Exploit (exploiting a good arm), (2) Innovate (asocial exploring for good arms), and (3) Observe (social exploring for good arms). Each agent has two parameters (c,pobs) to specify the decision: (i) c, the threshold value for Exploit. If the agent knows only arms whose payoffs are less than c, he chooses to explore. (ii)pobs, the probability for Observe when the agent explores. The parameters (c,pobs) of the agents are uniformly distributed. We introduce a scope nI for searching good arms in Innovate to control its cost. We determine optimal strategies of player using the complete knowledge about the bandit and the information of exploited arms by agents. We show which social or asocial exploring is optimal in (pc,nI) space. We conduct a laboratory experiment (67 subjects). If (pc,nI) is chosen so that social learning is far optimal than asocial learning, we observe the swarm intelligence effect. If (pc,nI) is in the region where asocial learning is optimal or comparable with social learning, we do not observe the effect.
  • 高野 雅典, 和田 計也, 福田 一郎
    論文ID: 30-6_JWEIN-D
    発行日: 2015/11/01
    [早期公開] 公開日: 2016/01/28
    ジャーナル フリー 早期公開
    Cooperative behaviors are common in humans and are fundamental to our society. Theoretical and experimental studies have modeled environments in which the behaviors of humans, or agents, have been restricted to analyze their social behavior. However, it is important that such studies are generalized to less restrictive environments to understand human society. Social network games (SNGs) provide a particularly powerful tool for the quantitative study of human behavior. In SNGs, numerous players can behave more freely than in the environments used in previous studies; moreover, their relationships include apparent conflicts of interest and every action can be recorded. We focused on reciprocal altruism, one of the mechanisms that generate cooperative behavior. This study aims to investigate cooperative behavior based on reciprocal altruism in a less restrictive environment. For this purpose, we analyzed the social behavior underlying such cooperative behavior in an SNG. We focused on a game scenario in which the relationship between the players was similar to that in the Leader game. We defined cooperative behaviors by constructing a payoff matrix in the scenario. The results showed that players maintained cooperative behavior based on reciprocal altruism, and cooperators received more advantages than noncooperators. We found that players constructed reciprocal relationships based on two types of interactions, cooperative behavior and unproductive communication.
  • 笹原 和俊
    論文ID: B-MDF02
    発行日: 2015/11/01
    [早期公開] 公開日: 2016/01/28
    ジャーナル フリー 早期公開
    The socialization of the Web changes the ways we behave both online and offline, leading to a novel emergent phenomenon called ``collective attention'' in which people's attention is suddenly concentrated on a particular real-life event. Visualizing collective attention is fundamental to understand human behavior in the digital age. Here we propose ``association networks'' to visualize usage-based, term-association patterns in a large dataset of tweets (short text messages) during collective attention events. First, we train the word2vec model to obtain vector representations of terms (words) based on semantic similarities, and then construct association networks: given some terms as seeds, the associated terms are linked with each other using the trained word2vec model, and considering the resulting terms as new seeds, the same procedure is repeated. Using two sets of Twitter data---the 2011 Japan earthquake and the 2011 FIFA Women's World Cup---we demonstrate how association networks visualize collective attention on these events. Provided the Japan earthquake dataset, the association networks that emerged from the most frequently used terms, such as earthquake and tsunami, exhibit distinct network structure related to people's attention during the earthquake, whereas one that emerged from emotion-related terms, such as great and terrible, shows a large connected cluster of negative terms and small clusters of positive terms. Furthermore, we compare association networks in different datasets, using the same seed terms. These results indicate the proposed method to be a useful tool for visualizing the implicit nature of collective attention that is otherwise invisible.
  • Hirahara Yuki, Toriumi Fujio, Sugawara Toshiharu
    論文ID: JWEIN-K
    発行日: 2015/11/01
    [早期公開] 公開日: 2016/01/28
    ジャーナル フリー 早期公開
    We propose an SNS-norms game to model behavioral strategies in social networking services (SNSs) and investigate the conditions required for the evolution of cooperation-dominant situations. SNSs such as Facebook and Google+ are indispensable social media for a variety of social communications ranging from personal chats to business and political campaigns, but we do not yet fully understand why they thrive and whether these currently popular SNSs will remain in the future. A number of studies have attempted to understand the conditions or mechanisms that keep social media thriving by using a meta-rewards game that is the dual form of a public goods game or by analyzing user roles. However, the meta-rewards game does not take into account the unique characteristics of current SNSs. Hence, in this work we propose an SNS-norms game that is an extension of Axelrod's metanorms game, similar to meta-rewards games, but that considers the cost of commenting on an article and who is most likely to respond to it. We then experimentally investigated the conditions for a cooperation-dominant situation, by which we mean many users continuing to post articles on an SNS. Our results indicate that relatively large rewards compared to the cost of posting articles and comments are required to evolve cooperation-dominant situations, but optional responses with lower cost, such as ``Like!'' buttons, facilitate the evolution. This phenomenon is of interest because it is quite different from those shown in previous studies using meta-rewards games. We also confirmed the same phenomenon in an additional experiment using a network structure extracted from real-world SNS data.
  • ~ テキスト情報のLOD化に向けたWeb APIの開発 ~
    川村 隆浩, 大須賀 昭彦
    論文ID: LOD-21
    発行日: 2016/01/06
    [早期公開] 公開日: 2016/01/28
    ジャーナル フリー 早期公開
    Linked Open Data (LOD) is recently attracting attention as a vast amount of distributed knowledge base on the Web.Thus, semi-structured data such as tables and hierarchical data in several domains have been triplified to the LOD.In the research area, however, triplification of unstructured data such as text and sensor data is actively studied as the next target.Therefore, we developed a Web API for mainly extracting triples from text data, which is useful for the triplification of text data.We defined two steps for the text triplication.The first step is the extraction of phrases, which correspond to triple <subject, verb, object>, location and time from a natural language sentence, and the second one is a conversion of the extracted phrases to the existing (or new) resources and properties in the LOD. In this paper, we first describe the service specification corresponding to the first step, technical background, and evaluation of the current extraction accuracy, then finally introduce some use cases of the service. Although this service adopts a novel combination of a restrictive method using ontology-based rules and an example-based machine learning method using conditional random field, based on probability distribution, the main cotribution of the service is in practical aspect, that is, mash-up of several natural language processing techniques as a text triplification service, and deployment as a Web API freely available for public use so that non-expert easily use it.
  • 黄 宏軒, 乙木 翔地, 堀田 怜, 川越 恭二
    論文ID: DSF-514
    発行日: 2016/01/06
    [早期公開] 公開日: 2016/01/08
    ジャーナル フリー 早期公開
    As the advance of embodied conversational agent (ECA) technologies, there are more and more real-world deployed applications of ECA's like the guides in museums or exhibitions. However, in these applications, the agent systems are usually used by groups of visitors rather than individuals. In such multi-user situation, which is more complex sophisticated than single user one, specific features are required. There can be difference in how and when to intervene in the conversation of others due to the variety of personality. In order to realize a more human-like and more helpful guide agent, this work tries to explore the relationship between personality and the willing to intervene in users' conversation as the role of a guide.
feedback
Top