Search Results 1-20 of 128

  • How does the Journal of Information Science and Technology Association read? An analysis of the download data from J-STAGE  [in Japanese]

    ONODERA Natsuo

    <p>電子ジャーナルサイトJ-STAGEのアクセス統計データを用いて，このサイトから公開されている『情報の科学と技術』に掲載された記事の本文ダウンロードデータを分析した。延べダウンロード数は漸次上昇しており，最近は月3万件程度で推移している。特集記事や連載記事など，非会員に6か月のエンバーゴ期間を設定している記事の多くは，発行当月多くのダウンロードがあった後大きく減少し，6か月経過後に …

    The Journal of Information Science and Technology Association 70(5), 273-277, 2020

    J-STAGE  Ichushi Web 

  • Stepwise Noise Elimination for Better Motivational and Advisory Texts Classification

    Swieczkowska Patrycja , Rzepka Rafal , Araki Kenji

    … In this paper, we present a method of distinguishing texts containing motivational advice from regular texts to sort out noise in training data for our dialogue system. … We achieved F-score of 0.94 and 0.97 with our proposed method. … Secondly, we were able to create a classifying algorithm that distinguishes motivational/advisory texts from regular ones. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 24(1), 156-168, 2020

    J-STAGE 

  • SPATIAL COMPOSITION AND PREMISES ARRANGEMENT OF TRADITIONAL MANCHU VILLAGE IN NORTHEAST CHINA:Case study on Shengli Village in Xinbin Manchu Autonomous County of Liaoning Province  [in Japanese]

    USHIJIMA Akira , YANG Dan , NAKAZONO Mahito , MISHIMA Sachiko

    … Background</p><p> The Manchurians living in northeast China, as one of the 55 ethnic minorities in China, have been protected their rights to use the minority language and maintain unique culture and customs. …

    Journal of Architecture and Planning (Transactions of AIJ) (762), 1715-1725, 2019-08

    J-STAGE  AIJ 

  • AI and linguistics  [in Japanese]

    名倉 秀人

    … Vacuum cleaners and microwave ovens talks. … "Smart speakers" can understand speech, process it and react by speech. … Speech understanding means the technology of speech-to-text. … Processing the text data needsmorphological analysis. … Speaking of the text data after processing needs voice synthesis. …

    東洋大学大学院紀要 = Bulletin of the Graduate School, Toyo University (55), 157-168, 2019-03

    IR 

  • Improvement of classification accuracy by large-scale language generation model:Classification analysis of TOPIX Core30 companies through LSTM  [in Japanese]

    Nishi Yoshihiro , Suge Aiko , Takahashi Hiroshi

    … However, the limitations in the number of available data sets usuallybecome the hurdle for the model accuracy. … In this study, Reuter's news texts were classified based on eachreturn through LSTM models. … As a result of the analysis, we found the prediction accuracy could be improvedby using texts generated by GPT-2. …

    Proceedings of the Conference of Transdisciplinary Federation of Science and Technology 2019(0), B-5-6, 2019

    J-STAGE 

  • Filtering Method for Twitter Streaming Data Using Human-in-the-Loop Machine Learning

    Suzuki Yu

    … <p>A large number of texts is posted daily on social media. … However, only a small portion of these texts is informative for a specific purpose. … If we accurately filter the texts, we can continuously obtain fresh and useful information in real time. …

    Journal of Information Processing 27(0), 404-410, 2019

    J-STAGE 

  • Implementation of Image Disclosure System Using IIIF in NINJAL  [in Japanese]

    高田 智和 , 福山 雅深 , 堤 智昭 , 小助川 貞次 , Tomokazu TAKADA , Masami FUKUYAMA , Tomoaki TSUTSUMI , Teiji KOSUKEGAWA

    国立国語研究所 研究系 言語変化研究領域東京農工大学 博士前期課程東京電機大学富山大学昨今，デジタル技術の進歩，学術政策におけるオープンサイエンス・オープンデータの推進と相まって，世界各国の様々な機関が所蔵する資料（主に古典籍）のデジタル画像化とインターネットを通じた公開が進んでいる。従来の公開では，単純な閲覧を目的とした場合，JPEG形式やTIFF形式のデジタル画像を提供する方式や専用ビューアを …

    国立国語研究所論集 (15), 163-176, 2018-07

    IR  DOI 

  • A Cross-Media Retrieval Algorithm Based on Consistency Preserving of Collaborative Representation

    Shang Fei , Zhang Huaxiang , Sun Jiande , Liu Li , Zeng Hui

    … In order to measure the similarity between data coming from different modalities, CR-CMR first takes the advantage of dictionary learning techniques to obtain homogeneous collaborative representation for texts and images, then, it considers the semantic consistency of different modalities simultaneously and maps the collaborative representation coefficients into an isomorphic semantic subspace to conduct cross-media retrieval. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 22(2), 280-289, 2018

    J-STAGE 

  • Modality-Reconstructed Cross-Media Retrieval via Sparse Neural Networks Pre-Trained by Restricted Boltzmann Machines

    Zhang Bin , Zhang Huaxiang , Sun Jiande , Wang Zhenhua , Wu Hongchen , Dong Xiao

    … <p>Cross-media retrieval has raised a lot of research interests, and a significant number of works focus on mapping the heterogeneous data into a common subspace using a couple of projection matrices corresponding to each modal data before implementing similarity comparison. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 22(5), 611-620, 2018

    J-STAGE 

  • Review Rating Prediction on Location-Based Social Networks Using Text, Social Links, and Geolocations

    WANG Yuehua , ZHONG Zhinong , YANG Anran , JING Ning

    … <p>Review rating prediction is an important problem in machine learning and data mining areas and has attracted much attention in recent years. … Most existing methods for review rating prediction on Location-Based Social Networks only capture the semantics of texts, but ignore user information (social links, geolocations, etc.), which makes them less personalized and brings down the prediction accuracy. …

    IEICE Transactions on Information and Systems E101.D(9), 2298-2306, 2018

    J-STAGE 

  • Digital Archive Newspaper Clippings Collection: The uniqueness and the tendency of its use  [in Japanese]

    SUEDA Makiko , HANAZAKI Kayoko

    <p>神戸大学附属図書館デジタル版新聞記事文庫は，神戸大学経済経営研究所の所蔵する明治末～1970年の新聞記事切抜帳コレクション約3,200冊のうち，戦後までの記事約38万件の画像と本文テキストを対象に電子化公開を進めるデジタルアーカイブである。2000年のサービス開始以来コンテンツの公開を続け，現在約30万件を公開する。本稿では，新聞記事文庫の成り立ちとその独自の価値を再確認するとと …

    The Journal of Information Science and Technology Association 68(9), 462-466, 2018

    J-STAGE 

  • Edo Cuisine and the NIJL-NW Project: Potentialities and problems in collaborative projects with the private sector  [in Japanese]

    MATSUBARA Megumi , KOMIYAMA Fumi , YAMAMOTO Kazuaki

    <p>国文学研究資料館（国文研）が進める歴史的典籍NW事業では，画像公開している古典籍をもっと自由に活用してもらう活動にも取り組んでいる。そのなかでも特に反響の大きかったのが「江戸料理」に関する事業で，人文学オープンデータ共同利用センター（CODH）などの研究機関や企業等とのコラボレーションに進展し，多くのメディアにも取り上げられた。そのあらましを述べたうえで，企業と連携していくなかで …

    The Journal of Information Science and Technology Association 68(6), 285-290, 2018

    J-STAGE 

  • Constructing text-to-speech systems for languages with unknown pronunciations

    Sawada Kei , Hashimoto Kei , Oura Keiichiro , Nankaku Yoshihiko , Tokuda Keiichi

    … To address this problem, we investigate a framework for automatically constructing a TTS system from a target language database consisting of only speech data and corresponding Unicode texts. … Then, a grapheme-to-phoneme converter and a statistical parametric speech synthesizer are constructed based on the obtained pseudo phonetic information. …

    Acoustical Science and Technology 39(2), 119-129, 2018

    J-STAGE 

  • Predicting the Difficulty Level of TED Videos by Readability Grade Level and Speed of Speech  [in Japanese]

    田淵 龍二

    … TED Talks are videos from expert speakers on education, business, science, technology and creativity, with subtitles. … Each subtitle file has texts and timing data of speech, so we can easily calculate its readability grade level and speed of speech. … We downloaded 205 TED Talk subtitle files from the website and analyzed 48,271 subtitles. …

    LET Kanto Journal 1(0), 61, 2017

    J-STAGE 

  • Construction of a Connectives Dictionary for Academic Writing Assistance System  [in Japanese]

    Nishina Kikuko , Yagi Yutaka , HODOŠČEK Bor , Abekawa Takeshi

    … We aim to construct an academic writing assistance system for learners of Japanese as a second language who are tasked with writing academic papers and reports during the course of their studies. …

    Mathematical Linguistics 31(2), 160-176, 2017

    J-STAGE 

  • Cross-Media Retrieval Based on Query Modality and Semi-Supervised Regularization

    Liu Yihe , Zhang Huaxiang , Liu Li , Meng Lili , Wang Yongxin , Dong Xiao

    … In this paper, we propose a novel cross-media retrieval method based on Query Modality and Semi-supervised Regularization (QMSR). … Taking the cross-media retrieval between images and texts for example, QMSR learns two couples of mappings for different retrieval tasks (i.e. using images to search texts (Im2Te) or using texts to search images (Te2Im)) instead of learning one couple of mappings. …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 21(7), 1211-1220, 2017

    J-STAGE 

  • Education and Training System for Dialysis Puncture Technique in Clinical Engineering  [in Japanese]

    KANEHIRA Ren , OHASHI Atsushi , Asai Emiko , FUJIMOTO Hideo

    … Within such a system, several problems which may mostly probably be encountered to an engineer when operating practical medical machines in hospital were selected and solutions with training methods for such problems were proposed. …

    The Proceedings of Mechanical Engineering Congress, Japan 2017(0), J2410102, 2017

    J-STAGE 

  • A Novel Linguistic Steganography Based on Synonym Run-Length Encoding

    XIANG Lingyun , WANG Xinhui , YANG Chunfang , LIU Peng

    … <p>In order to prevent the synonym substitution breaking the balance among frequencies of synonyms and improve the statistical undetectability, this paper proposed a novel linguistic steganography based on synonym run-length encoding. … Firstly, taking the relative word frequency into account, the synonyms appeared in the text are digitized into binary values and expressed in the form of runs. …

    IEICE Transactions on Information and Systems E100.D(2), 313-322, 2017

    J-STAGE 

  • Grasp of Disaster Situation and Support Need Inside Affected Area with Social Sensing – An Analysis of Twitter Data Before and After the 2011 Great East Japan Earthquake Disaster Occurring –

    Sato Shosuke , Hanaoka Kazumasa , Okumura Makoto , Koshimura Shunichi

    … This paper reports on a geo-information and content analysis of three million Twitter texts sampled from Japanese Twitter accounts for one month before and after the 2011 Great East Japan Earthquake disaster. … 1) The number of Twitter texts that include geotag (latitude and longitude information) is too small for reliable analysis. …

    Journal of Disaster Research 11(2), 198-206, 2016

    J-STAGE 

  • "Reading" Texts at University in the Age of the Digital Archive: Uncovering the Possibilities with Three Experiments as Part of the University of Tokyo's "New Library Project"  [in Japanese]

    TANISHIMA Kanta , ABE Takuya

    <p>本稿では，東京大学附属図書館の「新図書館計画」の一環で実施された，「読書」をテーマとする三つの実証実験を紹介する。一つ目は，専門家の知識をデジタルアーカイブのなかに埋め込み，資料群を構造化することで，図書館利用者と資料との出会いを支援する実験，二つ目は，電子書籍に文献の索引と注釈を機械的に生成する機能を組み込むことで，利用者の読書行為を補助する実験，そして三つ目は，書き込み共有機 …

    The Journal of Information Science and Technology Association 66(10), 518-524, 2016

    J-STAGE 

Page Top