Search Results 1-20 of 505

  • Binary Codeword Table for Multilevel Document Classification Using Information Theoretic Criterion  [in Japanese]

    雲居 玄道 , 八木 秀樹 , 後藤 正幸 , 平澤 茂一

    … A multilevel classification method based on error-correcting codes in a framework of coding theory is one of the powerful construction methods of a multilevel classifier. … In this study, we examine the performance for classification error of codeword construction methods for multilevel classifier based on this framework. … In terms of classification performance, there are correlations among binary discriminators, and the overall performance depends on the combination of binary discriminators. …

    情報処理学会論文誌数理モデル化と応用(TOM) 13(1), 1-12, 2020-03-25

    IPSJ 

  • Identifying breakthrough scientific papers

    Savov Pavel , Jatowt Adam , Nielek Radoslaw

    Citation analysis does not tell the whole story about the innovativeness of scientific papers. Works by prominent authors tend to receive disproportionately many citations, while publications by less …

    Information Processing & Management 57(2), 2020-03

    IR 

  • Document Classification using Poincare Embeddings  [in Japanese]

    逆瀬川 滉大 , 峯 恒憲 , 廣川 佐千男

    人工知能基本問題研究会 111, 18-22, 2020-01-29

  • SPATIAL INTEGRATION DESIGN IN CONTEMPORARY ART MUSEUMS THROUGH THE SUPERPOSITION OF "ROOMS LAYOUT" AND "FINISHES LAYOUT"  [in Japanese]

    MATSUSHIMA Jumpei , INUIYA Kakeru , MURATA Ryo , YASUDA Koichi

    … Secondly, we extract finishes on the spatial component faces and analyze its classification, arrangement and continuity; …

    Journal of Architecture and Planning (Transactions of AIJ) (767), 49-57, 2020-01

    J-STAGE  AIJ 

  • Toward Design of an Agent-based Writing Support System for the SOAP Note: A Content Analysis of the Video-based Survey

    Heryawan Lukman , Khotimah Purnomo Husnul , Sugiyama Osamu , Yamamoto Goshiro , Santos Luciano Henrique de Oliveira , Pramono Angga Eko , Okamoto Kazuya , Kuroda Tomohiro

    … <p>Subjective, objective, assessment, and plan (SOAP) notes are widely used by physicians to document clinical reasoning in assessing, diagnosing, and treating patients. … In Indonesia, medical coders who are independent from physicians assess SOAP notes to assign diagnostic codes and medical procedure codes based on the corresponding International Classification of Diseases standards. …

    Advanced Biomedical Engineering 9(0), 146-153, 2020

    J-STAGE 

  • An Idea of a Rough Set Theory Based Document Classification System

    KUREMATSU Masaki

    … <p>The document classification task is a well-known task for natural language processing. … In this paper, I propose a Rough Set Theory based document classification system. … First, the proposed system makes a decision table by combining the label of the document and terms extracted by the document frequency and reduction. …

    Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 32(4), 778-781, 2020

    J-STAGE 

  • Efficient patent search considering preliminary search by machine learning:Document vectorization method and application of patent classification to patent search  [in Japanese]

    ANDO Toshiyuki

    <p>特許調査の上流工程である予備検索課程に特許調査と機械学習の観点から着目して自分でできる調査の効率化の基礎検討を行うものである。ブラックボックス化を避ける為にも特許調査は、最近のAIシステムに丸投げという方向性は目指さず、「人」が行うべきところと機械学習で行った方が良いところを仕分けする。性能評価方法の考え方は商用のシステムの性能評価にも応用可能である。</p>< …

    Preprints of the Information Professional Symposium 2020(0), 43-48, 2020

    J-STAGE 

  • Towards Automatic Update of Patent Application Technical Trend Survey  [in Japanese]

    NANBA Hidetsugu

    <p>The Japan Patent Office carries out the patent application technical trend survey for fields in which the development of technologies is expected, or fields to which social attention is being …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 4Q3GS902-4Q3GS902, 2020

    J-STAGE 

  • An Idea of a Rough Set Theory Based Document Classification System with RT method  [in Japanese]

    KUREMATSU Masaki

    … <p>In this paper, I propose a Rough Set Theory based document classification system with RT method. … First, the proposed system makes a decision table by combining the label of documents and terms extracted by the document frequency. … To identify an unlabeled document, it converts this document to sample data by the same way for making samples and get the distance between this document and the unit space. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 3Rin454-3Rin454, 2020

    J-STAGE 

  • Urgency Prediction Based on Document Classification Considering Annotation Noise for Medical Consultation Texts  [in Japanese]

    FUKASAWA Yusuke , HASHIMOTO Naoya

    <p>In teleconsultation service, it is crucial to obtain as much information as possible from the pre-interview text provided by the user. In this study, we constructed a model that predicts medi …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 3Rin464-3Rin464, 2020

    J-STAGE 

  • Classification of Issue discussions in Open Source Software Projects using BERT or Automated ML  [in Japanese]

    YAMADA Yuki , HAZEYAMA Atsuo , OGAWA Yutaro

    … Thus, constructing a technic identifying information types of each sentences in a document is important. … (2) Results: As a result from trained models using AutoML and calculated the global importance using SHAP, the length of sentences, the position in the document and the time between comments are important. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 3Rin408-3Rin408, 2020

    J-STAGE 

  • Semantic Consistency Assessment of Visual and Text Content using Multimodal Deep Neural Networks  [in Japanese]

    SUZUKI Riko , KONISHI Mikito , IKEDA Junya , HAYASHI Daichi , FUKAI So , SUGAWARA Yu , MACHII Yusuke , YAMAURA Yusuke

    … <p>Semantic consistency assessment of an image and text inside a document is important task because readers refer the image to deepen understanding of text content. … We propose a novel approach combines binary classification and angular margin loss to acquire discriminative features. …

    Proceedings of the Annual Conference of JSAI JSAI2020(0), 3Q5GS901-3Q5GS901, 2020

    J-STAGE 

  • Verification on validity of classification method of official documents based on laws and regulations.  [in Japanese]

    SHIMBARU Toshiki

    … <p>  For the two administrative organizations as subjects, we verified on validity for the classification method of official documents based on laws and regulations. … By classifying documents based on a single point of view, it is expected that eliminates the risk of discrepancies in determining the document classification destination among users, improves the searchability of documents, and leads to more smooth sharing of documents.</p> …

    Records Management 78(0), 38-53, 2020

    J-STAGE 

  • Visualization of Potential Technical Solutions by SOM and Co-Clustering and its Extension to Multi-View Situation

    Nishida Yasushi , Honda Katsuhiro

    … Non-structured patent document data can be quantified through two different scheme: word level co-occurrence probability vectors and correlation coefficients of the generated co-occurrence probability vectors. … <i>Document</i> … Additionally, this paper also considers an extension to a multi-view situation, where each patent is characterized by additional patent classification system of <i>F-term</i> …

    Journal of Advanced Computational Intelligence and Intelligent Informatics 24(1), 65-72, 2020

    J-STAGE 

  • Automatic Classifying Self-Admitted Technical Debt Using N-Gram IDF

    Supatsara Wattanakriengkrai , Napat Srisermphoak , Sahawat Sintoplertchaikul , Morakot l Choetkiertiku , Chaiyong Ragkhitwetsagul , Thanwadee Sunetnanta , Hata Hideaki , Matsumoto Kenichi

    … Those studies proposed to use binary classification technique to predict whether a comment shows SATD. … In this paper, we therefore propose an approach using N-gram Inverse Document Frequency (IDF) and employ a multi-class classification technique to build a model that can identify different types of SATD. …

    2019-12-05

    IR 

  • Document cluster label estimation using word vectors  [in Japanese]

    淀川 翼 , 加登 一成 , 伊東 栄典

    … Finally, estimate appropriate labels of a document set using similarity of word vector and SVM feature words. … As an experiment, we apply proposed method to two document sets, The 20 newsgroups and Livedoor news corpus. … Both sets are used for classification problem. …

    人工知能学会研究会資料 SIG-SWO 49(3), 03-01-03-05, 2019-11-22

    IR 

  • Investigation of Positional Relations on Distributed Representation of Words Contributing to Contrast Word Identification  [in Japanese]

    奥村 雄輝 , 廣川 佐千男 , 竹内 和広

    電子情報通信学会技術研究報告 = IEICE technical report : 信学技報 119(213), 5-9, 2019-09-29

  • F-term Assigning Method based on Stepwise Multi-label Classification by Hierarchical Label Structure  [in Japanese]

    奈良 清仁 , 秋吉 政徳 , 吉新 喜市

    電気学会研究会資料. IS 2019(46-51・53-58), 25-28, 2019-08-29

  • Sentiment Classification Using N-Gram Inverse Document Frequency and Automated Machine Learning

    Rungroj Maipradit , Hata Hideaki , Matsumoto Kenichi

    … We propose a sentiment classification method with a general machine-learning framework. …

    2019-05-29

    IR 

  • Effect and Application of Additional Vector in Word2Vec  [in Japanese]

    内田 脩斗 , 吉川 大弘 , 古橋 武

    … In the field of natural language processing, many studies applying Word2Vec to syntactic analysis and document classification have been reported and its usefulness is suggested. … In addition, we conduct a document classification task using each distributed representation and report its usefulness. …

    情報処理学会論文誌数理モデル化と応用(TOM) 12(1), 23-31, 2019-03-15

    IPSJ 

Page Top