Updated on 2024/04/17

写真a

 
Okada Makoto
 
Organization
Graduate School of Informatics Department of Core Informatics Assistant Professor
School of Engineering Department of Information Science
Title
Assistant Professor
Affiliation
Institute of Informatics
Affiliation campus
Nakamozu Campus

Position

  • Graduate School of Informatics Department of Core Informatics 

    Assistant Professor  2022.04 - Now

  • School of Engineering Department of Information Science 

    Assistant Professor  2022.04 - Now

Degree

  • 博士(工学) ( Others )

Research Areas

  • Informatics / Kansei informatics

  • Informatics / Database

  • Informatics / Intelligent informatics

  • Informatics / Kansei informatics

  • Informatics / Intelligent informatics

  • Informatics / Theory of informatics

▼display all

Research Interests

  • Deep Learning

  • Natural Language Understanding

  • Natural Language Processing

  • 知識処理

  • Text Classification

  • natural language processing

Research subject summary

  • 種々の知識を用いた情報検索処理の改良

  • 自然言語を用いた知識処理

Research Career

  • 深層学習を利用した言語モデルを用いた評判分析

    知識処理、自然言語処理、深層学習、機械学習  Individual

    2014.04 - Now 

  • 機械学習を用いた言語データからの意見抽出

    自然言語処理、自然言語理解、知識処理  Individual

    2012.04 - Now 

  • 機械学習による要望抽出

    情報検索、自然言語処理、自然言語理解、知識処理  Individual

    2012.04 - Now 

Professional Memberships

  • Japan Society for Fuzzy Theory and Intelligent Informatics

    2022.04 - Now

  • 人工知能学会

    2014.04 - Now   Domestic

  • The Institute of Electrical Engineers of Japan

    2013.04 - Now

  • パーソナルコンピュータ利用技術学会

    2013.04 - 2022.03   Domestic

  • 日本農業普及学会

    2008.04 - Now   Domestic

  • 言語処理学会

    2002.04 - Now   Domestic

  • Information Processing Society of Japan

    1996.09 - Now

▼display all

Job Career (off-campus)

  • Osaka Metropolitan University   Graduate School of Informatics, Department of Core Informatics, Intelligent Informatics

    2022.04 - Now

  • Osaka Prefecture University   Graduate School of Engineering, Division of Electrical Engineering and Information Science, Department of Computer Science and Intelligent Systems

    2012.04 - 2022.03

  • - 大阪府立大学 理学系研究科 助手

    2005

  • - Osaka Prefecture University, College of

    2001

Papers

  • Paragraph Boundary Recognition in Novels for Story Understanding Reviewed

    R. Iikura, M. Okada, N. Mori

    Applyed Sciences 雑誌   Vol. 11 ( Iss. 12 )   5632 - 5632   2021.06

     More details

    Publishing type:Research paper (scientific journal)   Kind of work:Joint Work  

    The understanding of narrative stories by computer is an important task for their automatic generation. To date, high-performance neural-network technologies such as BERT have been applied to tasks such as the Story Cloze Test and Story Completion. In this study, we focus on the text segmentation of novels into paragraphs, which is an important writing technique for readers to deepen their understanding of the texts. This type of segmentation, which we call “paragraph boundary recognition”, can be considered to be a binary classification problem in terms of the presence or absence of a boundary, such as a paragraph between target sentences. However, in this case, the data imbalance becomes a bottleneck because the number of paragraphs is generally smaller than the number of sentences. To deal with this problem, we introduced several cost-sensitive loss functions, namely. focal loss, dice loss, and anchor loss, which were robust for imbalanced classification in BERT. In addition, introducing the threshold-moving technique into the model was effective in estimating paragraph boundaries. As a result of the experiment on three newly created datasets, BERT with dice loss and threshold moving obtained a higher F1 than the original BERT had using cross-entropy loss as its loss function (76% to 80%, 50% to 54%, 59% to 63%).

    DOI: 10.3390/app11125632

  • Automatic Paragraph Segmentation of Novels as Imbalanced Classification Reviewed

    Riku Iikura, Makoto Okada, Naoki Mori

    62 ( 3 )   891 - 902   2021.03

     More details

    Publishing type:Research paper (scientific journal)  

  • A Novel Segmentation Method of Novels for Story Analysis based on the distributed representation of sentences Reviewed

    Kiyohito Fukuda, Naoki Mori, Keinosuke Matsumoto, Makoto Okada

    18 ( 1 )   63 - 75   2019.03

     More details

    Publishing type:Research paper (scientific journal)  

  • An Evaluation Method of Words Tendency Depending on Time-series Variation and Its Improvements Reviewed

    EL-Sayed Atlam,Makoto Okada,Masami Shishibori,Jun-ichi Aoe

    International Journal of Information Processing 雑誌   Vol. 38 ( No. 2 )   157 - 171   2002.12

     More details

    Kind of work:Joint Work  

  • An Efficient Substring Search Method by Using Delayed Keyword Extraction and Compression Algorithm Reviewed

    M. Okada, K. Ando, Y. Hayashi, J. Aoe

    International Journal of Information Processing 雑誌   Vol. 37 ( Iss. 5 )   741 - 761   2001.12

     More details

    Kind of work:Joint Work  

    DOI: 10.1016/S0306-4573(00)00050-9

  • Two Improved Access Methods on Compact Binary (CB) trees Reviewed

    M. Shishibori, M. Koyama, M. Okada, J. Aoe

    International Journal of Information Processing 雑誌   Vol. 36 ( Iss. 1 )   379 - 399   2000.12

     More details

    Kind of work:Joint Work  

    DOI: 10.1016/S0306-4573(99)00035-7

  • A document classification method by using field association words Reviewed

    M. Fuketa, S. Lee, T. Tsuji, M. Okada, J. Aoe

    Information Science 雑誌   Vol. 126 ( Iss. 1-4 )   57 - 70   2000.07

     More details

    Kind of work:Joint Work   International / domestic magazine:International journal  

    DOI: 10.1016/S0020-0255(00)00042-6

  • キーワードの遅延抽出を考慮した文書検索構造の効率的構成法 Reviewed

    岡田 真, 安藤 一秋, 森田 和宏, 青江 順一

    情報処理学会論文誌 雑誌   Vol. 41 ( No. 4 )   1171 - 1179   2000.04

     More details

    Kind of work:Joint Work  

  • Design of a Compact Data Structure for the Patricia Trie Reviewed

    M. Shishibori, M. Okada, T. Sumitomo, J. Aoe

    IEICE Transactions on Information and Systems 雑誌   Vol. E81-D ( No. 4 )   364 - 371   1998.04

     More details

    Kind of work:Joint Work  

  • 格構造解析における概念階層の効率的判定アルゴリズム Reviewed

    小山 雅史,泓田 正雄,岡田 真,青江 順一

    情報処理学会論文誌 雑誌   Vol. 39 ( No. 3 )   551 - 558   1998.03

     More details

    Kind of work:Joint Work  

▼display all

MISC

  • 「大阪公立大学」新たなスタート International journal

    岡田 真

    電気学会誌   142 ( 11 )   721 - 721   2022.11( ISSN:13405551 ( eISSN:18814190

     More details

    Authorship:Lead author, Corresponding author   Publishing type:Article, review, commentary, editorial, etc. (scientific journal)   Kind of work:Single Work   International / domestic magazine:Domestic journal  

    <p>2022年4月より筆者の所属だった「大阪府立大学」は大阪市が設置運営している「大阪市立大学」と合併して,日本で最大級の公立大学「大阪公立大学」が誕生することと</p>

    DOI: 10.1541/ieejjournal.142.721

Presentations

  • 英語学習者における対話への深層言語モデルを用いた補完方法の検討 Domestic conference

    2024.03 

     More details

    Presentation type:Oral presentation (general)  

  • Omuokdlb at the NTCIR-17 QA Lab-Poliinfo-4 Task International conference

    Hidenori Yamato, Takaaki Fukunaga, Makoto Okada and Naoki Mori

    The 17th NTCIR Conference  2023.12  NII

     More details

    Presentation type:Poster presentation  

    Venue:Tokyo, Japan  

    DOI: https://doi.org/10.20736/0002001302

  • Genetic Algorithm for Prompt Engineering with Novel Genetic Operators International conference

    Hiroto Tanaka, Naoki Mori and Makoto Okada

    15th International Congress on Advanced Applied Informatics (IIAI AAI 2023-Winter)   2023.12  International Institute of Applied Informatics (IIAI)

     More details

    Presentation type:Oral presentation (general)  

    Venue:Bari, Indonasia  

  • Trainable Weighted Pooling Method for Text Classification with BERT International conference

    Hidenori Yamato, Makoto Okada and Naoki Mori

    15th International Congress on Advanced Applied Informatics (IIAI AAI 2023-Winter)   2023.12  International Institute of Applied Informatics (IIAI)

     More details

    Presentation type:Oral presentation (general)  

    Venue:Bari, Indonasia  

  • Analysis of LLM-Based Narrative Generation using the Agent-based Simulation International conference

    Naoto Aoki, Naoki Mori and Makoto Okada

    15th International Congress on Advanced Applied Informatics (IIAI AAI 2023-Winter)   2023.12  International Institute of Applied Informatics (IIAI)

     More details

    Presentation type:Oral presentation (general)  

    Venue:Bari, Indonasia  

  • Validation of a Japanese essay proofreading method based on sentence similarity Domestic conference

    Yusuke Ikeda, Makoto Okada, Naoki Mori

    2023.09 

     More details

    Presentation type:Oral presentation (general)  

    DOI: 10.14864/fss.39.0_923

  • An Investigation of Extraction Method for Evaluation Target Words and Evaluation Words Using Deep Language Model for Aspect-Based Summarization Domestic conference

    Hayato Tanaka, Makoto Okada, Naoki Mori

    2023.09 

     More details

    Presentation type:Oral presentation (general)  

    DOI: 10.14864/fss.39.0_439

  • 日本語母語話者の英語対話コーパスに対する深層言語モデルを用いた単語予測の分析と評価 Domestic conference

    岡田 真, 竹内 和広

    日本教育工学会研究報告集  2023.07  一般社団法人 日本教育工学会

     More details

    Presentation type:Oral presentation (general)  

    <p>第2言語習得に取り組む学生のカリキュラムとして第2言語で対話をしつつ定められたタスクをこなすものがある.この際に学生の習熟度の差によって会話が途切れるなど滑らかな会話にならなかったり対話の際に意味がとり切れず理解の食い違いや誤解が生じる場合がある.その際にネイティブスピーカであればどのように会話していたかという想定の事例を示すことは学習者のスキル向上に有効であると期待できる.しかしネイティブスピーカに容易に協力が得られない場合も容易に想定できる.本論文では深層学習による大規模言語モデルをネイティブスピーカの言語能力を表すものと仮定して,それを利用することで既存の対話情報中の単語を補完・推測させて,その結果を確認して,ネイティブスピーカの会話を推定できるかどうかその可能性を検証する.</p>

    DOI: 10.15077/jsetstudy.2023.2_301

  • A Proposal of a Method to Estimate Automatically Evaluations of Detailed Topics of Travelers' Reviews Domestic conference

    2016.05 

     More details

    Presentation type:Oral presentation (general)  

  • A Method of Sentiment Analysis of Reviews of Accommodation Users Considering Their Using Status Domestic conference

    2015.06 

     More details

    Presentation type:Oral presentation (general)  

  • An Investigation of Effectiveness of Estimation String Pattern to Extract Sentiment Information from Customer Reviews of Tourists Domestic conference

    2015 

     More details

    Presentation type:Oral presentation (general)  

  • An Investigation of an Effectiveness of Estimation Sentence Patterns for a Classification of Customer Reviews Considering Their Conditions

    2014 

  • Extraction of Problems of Start-Farming from News Articles and Questionnaire Surveys

    OKADA Makoto, HIROKAWA Sachio, HASHIMOTO Kiyota

    2013.09 

  • An Investigation of Efficiency of a Method of Data Mining and Visualization : Using Questionnaire Survey Results for New Farming Applicants Domestic conference

    OKADA Makoto, HIROKAWA Sachio, HASHIMOTO Kiyota

    2013.05 

     More details

    Presentation type:Oral presentation (general)  

  • Toward Multi-Lingual Knowledge Extraction from Travelers' Reviews International conference

    HASHIMOTO Kiyota, OKADA Makoto, TAKEUCHI Kazuhiro, HIROKAWA Sachio

    2012.12 

     More details

    Presentation type:Oral presentation (general)  

  • Extraction of Onomatopoeic Expressions in Japanese and Korean and their Applications

    HASHIMOTO Kiyota, OKADA Makoto, TAKEUCHI Kazuhiro, HIROKAWA Sachio

    電気学会研究会資料. IS, 情報システム研究会  2012.05 

  • An Extraction Method of Landmark Information from Documents on the Web

    OKADA Makoto, MURAI Yuki

    2011.05 

  • An Method to Extract Comparative Relations from Texts of Reviews

    OKADA Makoto, NISHIKAWA Takaya

    2011.05 

  • Retrieval from databases by fuzzy queries in the Internet Domestic conference

    UMANO Motohide, MATSUO Takeaki, SETA Kazuhisa, OKADA Makoto

    2002.08 

     More details

    Presentation type:Oral presentation (general)  

  • An Automatic Clustering Method Using Keyword Extraction

    1997 

  • キーワード抽出を用いた文書自動分類手法 Domestic conference

    情報処理学会第55回全国大会講演論文集(分冊3)  1997 

     More details

    Presentation type:Oral presentation (general)  

▼display all

Outline of collaborative research (seeds)

  • 大規模文書データからの知識自動抽出

  • カスタマーレビューなどを対象とした評判分析

Charge of on-campus class subject

  • 基幹情報学特別研究1

    2023   Intensive lecture   Graduate school

  • 工学倫理

    2023   Weekly class   Undergraduate

  • 情報工学演習1

    2023   Weekly class   Undergraduate

  • 論理演算工学

    2023   Weekly class   Undergraduate

  • 情報工学基礎演習2

    2023   Weekly class   Undergraduate

  • 情報システム概論

    2023   Weekly class   Undergraduate

  • 基幹情報学特別研究2

    2023   Intensive lecture   Graduate school

  • Computational Theory

    2023   Weekly class   Undergraduate

  • 論理演算工学

    2022   Weekly class   Undergraduate

  • 情報工学基礎演習2

    2022   Weekly class   Undergraduate

  • Computational Theory

    2022    

  • 情報システム概論/選:工〈航空・海洋・電子〉

    2022   Weekly class   Graduate school

  • Computational Theory

    2021    

  • Logical Operations

    2021    

  • Introduction to Programming

    2021    

  • Introduction to Information System

    2021    

  • Introduction to Programming

    2021    

▼display all

Charge of off-campus class subject

  • 人工知能

    2023.04
    -
    2023.08
    Institution:Setsunan University

     More details

    Level:Undergraduate (specialized) 

Social Activities

  • 模擬講義(京都府立南陽高校) 会話するコンピュータ

    2018.04 - 2019.03

  • 出張講義 会話するコンピュータ

    2012.04 - 2013.03

  • 模擬講義(富山県立新湊高校学生対象) 会話するコンピュータ

    2011.04 - 2012.03

  • 出張講義 会話するコンピュータ

    2010.04 - 2011.03

  • 出張講義 会話するコンピュータ

    2010.04 - 2011.03

  • 出張講義 会話するコンピュータ

    2009.04 - 2010.03

  • 出張講義 会話するコンピュータ

    2008.04 - 2009.03

▼display all

Visiting Lectures ⇒ Link to the list of Visiting Lectures

  • 会話するコンピュータ

    Category:Literature (literature, philosophy, history, art, human behavior, language, culture, society / gender), Engineering (machinery, electronics / physics, electrical / electronics, electrical information, chemical biotechnology, architecture, cities (civil engineering / environment), material chemistry, aerospace, marine systems, applied chemistry, chemistry, materials)

     More details

    Audience:High school students, College students, General

    Keyword:自然言語処理, 自然言語理解, 談話理解 

    ヒトと会話ができるコンピュータはどうしたら作れるか、また、現在のコンピュータとはどこまで会話できるのか、さらにどのような問題がまだ残っているのかについて皆さんと考えてみましょう.