人工知能学会論文誌
検索
OR
閲覧
検索
31 巻 , 5 号
選択された号の論文の4件中1~4を表示しています
    • |<
    • <
    • 1
    • >
    • >|
原著論文
  • 早矢仕 晃章, 大澤 幸生
    31 巻 (2016) 5 号 p. A-G15_1-9
    公開日: 2016/08/15
    ジャーナル フリー

    The potential desire of companies for creating values by combining data from different domains has been increased. In order to lead data-driven innovations, a market of data is expected to enhance this combination and data exchange through the communication among stakeholders. Innovators Marketplace on Data Jackets (IMDJ) is a gamified workshop for discovering the value of data by discussing the combination of Data Jackets, which supports creativity toward innovations and activates a market of data. A Data Jacket is meta-data, i.e., a summary of a dataset. Even if the data is not open, a Data Jacket enables participants to consider the latent value of datasets through creative communication. In this study, we discuss a system for structuring and reusing knowledge of data utilization, which are created in the workshops of IMDJ. By modeling and structuring knowledge not only with datasets, but also with solutions or requirements, it is expected to be possible to retrieve important information about solving problems. By implementing structured knowledge of data utilization using RDF (Resource Description Framework) and designing the interface for extracting accurate information for users, we propose the retrieval system named Data Jacket Store, and evaluate the performance.

    抄録全体を表示
  • 岩沼 宏治, 山本 泰生, 福田 翔士
    31 巻 (2016) 5 号 p. B-G52_1-10
    公開日: 2016/08/31
    ジャーナル フリー

    In this paper, we propose a novel online ϵ-approximation algorithm, called LC-CloStream, for mining closed frequent itemsets embedded in a transactional stream. LC-CloStream is based on an incremental/cumulative intersection method and ϵ-elimination proposed by Lossy Counting algorithm. We show, LC-CloStream is essentially incomplete, but is still semi-complete for mining frequent closed itemsets in a stream. Moreover, we prove the completeness of extracting frequent itemsets and the ϵ-approximation for estimating the frequency. We also show several good performances of the experimental evaluation for LC-CloStream.

    抄録全体を表示
  • 渡邉 亮彦, 笹野 遼平, 高村 大也, 奥村 学
    31 巻 (2016) 5 号 p. C-G41_1-12
    公開日: 2016/10/05
    ジャーナル フリー

    Web page recommender systems usually provide users with titles and snippets of recommended pages when the systems present a list of recommendations. Snippets help users judge whether recommended web pages are relevant or not. However, while search engines usually show a text span around a search query as a snippet, web page recommender systems cannot leverage the snippet generation methods used by search engines because the recommender systems have no search queries. Web page recommender systems thus generally use lead sentences, i.e. the first sentences of web pages, as a snippet, but lead sentences are not necessarily relevant to user’s interest. Furthermore since user’s information needs can be different from each other, personalized snippets are desirable to support user’s relevance judgment. Therefore, we propose a new method to generate personalized snippets for web page recommender systems that uses reasons why the web pages are recommended to the user. This use of reasons enables snippets to reflect the interest of the user. Furthermore, since our formulation does not depend on a certain recommender system, our method can be applied to diverse recommender systems. The experimental result on manually created dataset shows that our method is superior to the existing method and generic summarization model in terms of ROUGE-2. In addition, our method achieves comparable performance with the lead method despite that our method restricts itself to sentence selection while the lead method is free to extract a part of a sentence at the end of its snippets.

    抄録全体を表示
  • 赤尾 優希, 林 雄介, 平嶋 宗
    31 巻 (2016) 5 号 p. D-G33_1-10
    公開日: 2016/10/05
    ジャーナル フリー

    We have developed an interactive learning environment for problem-posing of arithmetical word problem as sentence integration that is called MONSAKUN. We have already verified usefulness of MONSAKUN through several classes in a few elementary schools. In this research, to make learning by problem-posing with MONSAKUN more effective for the structural understanding, we have designed an exercise to make the learner engage in self-explanation of their problem-posing. In MONSAKUN, a learner is required to pose a problem by selecting three sentence cards from a set of sentence cards. The cards that are not necessary to pose the problem are called dummy cards. Therefore, the process of problem-posing is regarded as finding process of the dummy cards. Therefore, in this research, the activity of self-explanation of the problem-posing is regarded as the activity to explain a card as a dummy one. Then, the explanation is designed as modification of the original assignment of problem-posing in order to make an assignment that is allowed to use the dummy card to pose a problem. We have developed an interactive environment where a learner is required this modification. In this paper, we report an experimental use of this environment in an elementary school and the results.

    抄録全体を表示
    • |<
    • <
    • 1
    • >
    • >|
feedback
Top