Search Results 1-20 of 56

  • 1 / 3
  • Detection of Mergeable Wikipedia Articles Utilizing Multiple Similarity Measures

    Renzhi Wang , Mizuho Iwaihara

    Wikipedia is the largest online encyclopedia, in which articles are edited by different volunteers with different thoughts and styles. … According to Wikipedia Guidelines for article merge, in the duplicate case, the article pairs are covering exactly the same contents. …

    情報処理学会論文誌データベース(TOD) 13(1), 2020-01-27

    IPSJ 

  • Topic Analysis in Local Assemblies Using Word Embeddings Obtained from Large-scale Local Assembly Minutes  [in Japanese]

    SASAKI Minoru , OTOTAKE Hokuto , KIMURA Yasutomo

    <p>本研究では,地方議会会議録に対して,地方議会でどのような話題が議論されているかについてテキストマイニング手法を利用した分析を行う.既存研究では話題の分析を行う際に,最も適切な単語単位はどの程度なのか,大規模な都道府県議会会議録から得られた単語の分散表現が利用可能なのかについて研究が行われていない.本稿では,NTCIR14 Segmentation task で利用されたデータセッ …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4Rin159-4Rin159, 2020

    J-STAGE 

  • Detection of Mergeable Wikipedia Articles Utilizing Multiple Similarity Measures

    Wang Renzhi , Iwaihara Mizuho

    … <p>Wikipedia is the largest online encyclopedia, in which articles are edited by different volunteers with different thoughts and styles. … According to Wikipedia Guidelines for article merge, in the duplicate case, the article pairs are covering exactly the same contents. …

    Journal of Information Processing 28(0), 178-191, 2020

    J-STAGE 

  • Stance Detection Attending External Knowledge from Wikipedia

    Kazuaki Hanawa , Akira Sasaki , Naoaki Okazaki , Kentaro Inui

    … We build a new stance detection dataset consisting of 6,701 tweets on seven topics with associated Wikipedia articles. … This paper also presents a method of extracting related concepts and events from Wikipedia articles. … Our experimental results demonstrate that the proposed method, using knowledge extracted from Wikipedia, can improve stance detection performance.------------------------------This is a preprint of an article intended for publication Journal ofInformation Processing(JIP). …

    情報処理学会論文誌データベース(TOD) 12(3), 2019-07-17

    IPSJ 

  • Stance Detection Attending External Knowledge from Wikipedia

    Hanawa Kazuaki , Sasaki Akira , Okazaki Naoaki , Inui Kentaro

    … We build a new stance detection dataset consisting of 6, 701 tweets on seven topics with associated Wikipedia articles. … This paper also presents a method of extracting related concepts and events from Wikipedia articles. … Our experimental results demonstrate that the proposed method, using knowledge extracted from Wikipedia, can improve stance detection performance.</p> …

    Journal of Information Processing 27(0), 499-506, 2019

    J-STAGE 

  • Construction of Causal Networks for Risk Finding Considering Word Polarities  [in Japanese]

    IGARASHI Hiroaki IGARASHI , SAKAJI Hiroki , IZUMI Kiyoshi , SHIMADA Takashi , SUDA Shintaro

    <p>決算短信の因果関係ネットワークを構築する実験を行った.因果関係を決算短信から抽出し,表現の類似度を算出してネットワークを構築した.類似度の計算には日本語版ウィキペディアのコーパスから作成したword2vecモデルを使用し,単語の重要度を表すidf値の組み合わせることで,単語ベクトルから因果関係表現のベクトルを獲得した.また、極性辞書を用いて因果表現の極性の反転を捉えることで,wo …

    Proceedings of the Annual Conference of JSAI JSAI2019(0), 2O3J1304-2O3J1304, 2019

    J-STAGE 

  • Detection of mergeable Wikipedia articles based on multiple embedding results (データ工学)

    Wang Renzhi , Iwaihara Mizuho

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 117(374), 79-83, 2017-12-22

  • Generating Wikipedia-Like Biographical Sentences from Web People Search Results

    Murakami Harumi , Konishi Toshimune , Ura Yoshinobu

    … We extracted attribute information about people (birth date, death date, birthplace, vocation, organization, and position) from the HTML files of person clusters that were manually classified into individuals and generated biographical sentences whose style resembles the first sentence of Wikipedia. …

    IIAI International Congress on Advanced Applied Informatics, 995-996, 2017

    IR 

  • PRELIMINARY STUDY ON DETECTION OF NEWSPAPER TREND AMONG THEIR PUBLISHERS USING TEXT-MINING APPROACH  [in Japanese]

    市川 祐太

    … We collected online articles of those papers and Wikipedia as a supplemental data, and (1) divided them into set of each single words using morphological analysis, (2) obtained vector representation of each word by the word2vec methodology, (3) adjusted vector orientation based on the value registered on the Semantic orientation dictionary, and (4) compressed the vector dimension with t-SNE (t-distributed Stochastic Neighbor Embedding) and PCA(Principal Component Analysis) for data visualization. …

    法政大学大学院紀要. 理工学・工学研究科編 = 法政大学大学院紀要. 理工学・工学研究科編 (57), 1-5, 2016-03-24

    IR  DOI 

  • On Ranking and Mining Universities with the Encyclopedia Wikipedia

    Zongjian Li , Cong Li , Xiang Li

    IEICE Proceeding Series (48), A2L-C-2, 2016

    DOI 

  • Prediction of the Winning Technology for Mobile Internet Access : 3G/4G vs. WiFi(<Special Issue>Smart Mobile Innovation)

    JUNG Dong-gill

    … Specifically, a text mining technique was applied to discover the underlying bias towards one of the two technologies in the English Wikipedia. … The bias will be regarded as a collective intelligence of Wikipedia, providing an answer for the prediction. … The result of the programming experiment turned out that the English Wikipedia didn't show any bias towards one of the two technologies, i.e. it was neutral between the two. …

    Journal of Information and Management 36(1), 41-51, 2015

    J-STAGE 

  • Comparison of use of words between program code and the corresponding document to identify implementation pattern  [in Japanese]

    山下 大貴 , 竹内 和広

    ソフトウェアエンジニアリングシンポジウム2014論文集 (2014), 176-181, 2014-08-25

    IPSJ 

  • An Attempt for Automatic Acquisition of Attribute Frames in the Integrated Narrative Generation System  [in Japanese]

    ONO Jumpei , AKIMOTO Taisuke , OGATA Takashi

    … 本稿では,筆者らの統合物語生成システムにおける名詞概念辞書の拡張の一環として,名詞概念の属性フレームをWikipediaに存在する説明文から自動獲得する試みについて述べる.属性フレームとは,個々の名詞概念(一般名詞概念と固有名詞概念の両方を含む)を他と区別する特徴・性質の定義に相当し,この情報に基づいて物語の登場人物や物,場所が構成される.今回は特に,西山の言語学的研究を援用して,説明文の構文的なパ …

    IEICE technical report. Natural language understanding and models of communication 114(81), 47-52, 2014-06-14

  • Consumer Trend Prediction System Using Web Mining  [in Japanese]

    Hozumi Jun , Iitsuka Shuhei , Nakayama Kotaro , Takasu Masakazu , Shimada Eriko , Suga Chizuru , Nishiyama Keita , Matsuo Yutaka

    … Herein, we design a consumption trend calculating system that incorporates web mining. … Specifically, we use web mining of data elicited from search counts on search engines, tweet counts from Twitter, and article data from Wikipedia to calculate consumption trends based on weekly manga sales data in Japan. …

    Transactions of the Japanese Society for Artificial Intelligence 29(5), 449-459, 2014

    J-STAGE 

  • Mining Knowledge on Relationships between Objects from the Web

    ZHANG Xinpeng , ASANO Yasuhito , YOSHIKAWA Masatoshi

    Mining knowledge about relationships on Wikipedia has been studied. … By utilizing the objects constituting relationships mined from Wikipedia, we propose a new method to search images with surrounding text that include knowledge about relationships on the Web. … Enishi supplies a wealth of diverse knowledge including images with surrounding text to help users to understand relationships deeply, by complementarily utilizing knowledge from Wikipedia and the Web. …

    IEICE Transactions on Information and Systems E97.D(1), 77-88, 2014

    J-STAGE 

  • An approach for extracting concerned area of Twitter users by category information in Wikipedia  [in Japanese]

    HU Yinjun , TANIDA Yasuo

    … 本稿では,Wikipediaのカテゴリ特性に注目し,Wikipediaのカテゴリネットワークを利用してTwitterユーザの関心分野を抽出する手法を提案する.Twitterのデータには,語義曖昧性が多数存在するため,本研究では,まずWikipedia のカテゴリ「曖昧さ回避」を用いてTwitter データにおける語義曖昧性の解消をする.そして,Wikipediaのカテゴリネットワークを情報資源として,曖昧性解 …

    IEICE technical report. Natural language understanding and models of communication 113(213), 17-21, 2013-09-12

  • QUERY CLASSIFICATION BY EXPLOITING WIKIPEDIA AND WEB KNOWLEDGE

    DUAN JIANYONG , ZHANG MEI , LIU HUI

    ICIC express letters. Part B, Applications : an international journal of research and surveys 4(1), 175-181, 2013-02

  • A Generalized Flow-Based Method for Analysis of Implicit Relationships on Wikipedia

    Zhang Xinpeng , Asano Yasuhito , Yoshikawa Masatoshi

    … We focus on measuring relationships between pairs of objects in Wikipedia whose pages can be regarded as individual objects. … Two kinds of relationships between two objects exist: in Wikipedia, an explicit relationship is represented by a single link between the two pages for the objects, and an implicit relationship is represented by a link structure containing the two pages. …

    IEEE Transactions on Knowledge and Data Engineering 25(2), 246-259, 2013-02

    IR 

  • Community Detection from Signed Networks  [in Japanese]

    Sugihara Takahiko , Liu Xin , Murata Tsuyoshi

    … Community detection from networks is one of the important topics in link mining. … Our method enables us to detect communities from large scale real-world signed networks which represent relationship between users on websites such as Wikipedia, Slashdot and Epinions. …

    Transactions of the Japanese Society for Artificial Intelligence 28(1), 67-76, 2013

    J-STAGE 

  • How can the Web help Wikipedia? A Study of Information Complementation of Wikipedia by the Web

    Damien Eklou , Yasuhito Asano , Masatoshi Yoshikawa

    Wikipedia is a helpful tool because it is the largest, most-popular general reference site on the Internet. … Most search engines rank Wikipedia pages among the top listed results. … However, because many articles on Wikipedia are manually updated by users, several articles lack information and must be upgraded. …

    情報処理学会論文誌データベース(TOD) 5(3), 64-74, 2012-09-28

    IPSJ 

  • 1 / 3
Page Top