Rchr
J-GLOBAL ID:200901069857545387   Update date: Nov. 18, 2024

RZEPKA Rafal

ジェプカ ラファウ | RZEPKA Rafal
Affiliation and department:
Job title: 助教
Homepage URL  (1): http://kabura.info
Research field  (6): Intelligent informatics ,  Sensitivity (kansei) informatics ,  Philosophy and ethics ,  Cognitive sciences ,  Robotics and intelligent systems ,  Learning support systems
Research keywords  (8): Moral Machines ,  Artificial Intelligence ,  Artificial General Intelligence ,  Natural Language Processing ,  Common Sense Knowledge ,  Affective Computing ,  Machine Ethics ,  machine intelligence
Research theme for competitive and other funds  (15):
  • 2023 - 2026 技術流出防止のための、人工知能による新規のガイダンスシステムの開発
  • 2022 - 2025 Creation and Evaluation of Tacit Knowledge Based on Semantic Primes
  • 2020 - 2025 AI systems that can be explained in language based on knowledge and reasoning
  • 2020 - 2023 Development of Interactive Advisory System for Security Export Control
  • 2017 - 2022 Development of a System for Collecting Context Data for Large-Scale Inverse Reinforcement Learning
Show all
Papers (267):
  • Huizhong Ji, Rafal Rzepka. Fame Bias - Large Language Models Change Their Judgement Depending on Personal Name. 2025
  • Michal Ptaszynski, Pawel Dybala, Rafal Rzepka. Application of Artificial Intelligence Methods in Processing of Emotions, Decisions, and Opinions. Applied Sciences. 2024
  • Lu Wang, Sho Isomura, Michal Ptaszynski, Pawel Dybala, Yuki Urabe, Rafal Rzepka, Fumito Masui. The Limits of Words: Expanding a Word-Based Emotion Analysis System with Multiple Emotion Dictionaries and the Automatic Extraction of Emotive Expressions. Applied Sciences. 2024
  • Joanna Szwoch, Mateusz Staszkow, Rafal Rzepka, Kenji Araki. Limitations of Large Language Models in Propaganda Detection Task. Applied Sciences. 2024
  • Rafal Rzepka, Ryoma Shinto, Kenji Araki. Semantic Primes-Inspired Tacit Knowledge Dataset for Simulating Basic Perception Capabilities of Cognitive Architectures. 2024
more...
MISC (142):
  • 阿部有紗, ジェプカ・ラファウ, 荒木健治. DanStoデータセットを用いた大規模言語モデルの否定理解の性能評価. 2024度人工知能学会全国大会. 2024
  • 岡田憩, ジェプカ・ラファウ, 荒木健治. 常識知識グラフによる知識拡張プロンプトの有効性. 2024度人工知能学会全国大会. 2024
  • 進藤稜真, ジェプカラファウ, 竹下昌志, 荒木健治. ヒューリスティックと遺伝的アルゴリズムを用いた自動プロンプトチューニング手法. 言語処理学会第30回年次大会(NLP2024), P9-8. 2024
  • 竹下昌志, 連慎治, ジェプカラファウ, 荒木健治. 日本語徳倫理データセットの開発に向けて:英語データセットの翻訳と日本語データセットの比較. 言語処理学会第30回年次大会(NLP2024), P3-26. 2024
  • Rafal Rzepka, Kacper Dudzic, Arisa Abe, Kenji Araki. DanSto - Japanese Dataset of Short Stories for Evaluating Context Understanding. 2024. SIG-AGI-026-06
more...
Books (11):
  • Obtaining hints to understand language model-based moral decision making by generating consequences of acts
    Elsevier 2024 ISBN:9780443159916
  • Corpus Linguistics and Discourse Annotations. International Journal of Computational Linguistics and Chinese Language Processing (IJCLCLP)
    2022
  • The 7th Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA 2021) - CEUR Workshop Proceedings vol. 2935
    2021
  • Advances in Intelligent Systems and Computing
    2021 ISBN:9783030964504
  • Joint Proceedings of the Workshops on Linguistic and Cognitive Approaches to Dialog Agents (LaCATODA 2019) and on Bridging the Gap Between Human and Automated Reasoning (BtG 2019) CEUR Workshop Proceedings vol. 2935
    2019
more...
Lectures and oral presentations  (17):
  • Examples of NLP applications in detecting immoral behavior in Japanese
    (The Fifth Conference on Information theories and information analysis in forensics, criminology, law and security sciences 2023)
  • 人工知能の基礎知識
    (札幌まちづくり「おしゃべりサロン」 2023)
  • 人工知能と未来を考える
    (苫小牧市科学センター「サイエンス・カフェ」 2023)
  • 人工知能と倫理
    (苫小牧市科学センター「サイエンス・カフェ」 2023)
  • Large Language Models - Sophisticated Autocomplete Tools or a Big Step Towards AGI?
    (2022)
more...
Works (11):
  • JCommonsenseMorality
    Masashi Takeshita, Rafal Rzepka, Kenji Araki 2023 -
  • Semantic primes prompts in Japanese (approx. 64,000 annotated cognitive knowledge data samples
    Rafal Rzepka 2023 -
  • ROCStories-jp: approx. 55,000 English stories with alternative endings automatically translated to Japanese
    Rafal Rzepka 2023 -
  • DanSto (Dangerous Stories) approx. 8,000 five-sentence stories in Japanese based on DanSen dataset
    Rafal Rzepka 2023 -
  • CISTEC FAQ-based Trade Security QA dataset
    Rafal Rzepka, Akihiko Obayashi 2022 -
more...
Education (2):
  • 2001 - 2004 Hokkaido University Faculty of Engineering Division of Electrical, Electronic and Information Engineering
  • 1993 - 1999 Adam Mickiewicz University Department of Neophilology
Professional career (1):
  • PhD (Engineering) (Hokkaido University)
Work history (8):
  • 2024/09 - 現在 Hokkaido University Faculty of Information Science and Technology Associate Professor
  • 2007/04 - 2024/08 Hokkaido University Faculty of Information Science and Technology Assistant Professor
  • 2017/06 - 2020/03 RIKEN Center for Advanced Intelligence Project (AIP) Visiting Researcher
  • 2019/02 - 2019/03 Queensland University of Technology Digital Media Research Center
  • 2017/01 - 2017/09 Australian National University Centre of Excellence for the Dynamic of Language Visiting Fellow
Show all
Committee career (79):
  • 2023/07 - 現在 EMNLP Ethics Committee Member
  • 2023/06 - 現在 Japanese Society of Artificial Intelligence Board of Representatives
  • 2021 - 現在 Information Processing and Management Journal Program Committee Member
  • 2020/12 - 現在 人工知能学会 国際セッション オーガナイザー
  • 2019 - 現在 New Generation Computing Journal Program Committee Member
Show all
Awards (13):
  • 2023/04 - LTC 2023 Conference Best Paper Award Sentiment Analysis of Polish Online News Covering Controversial Topics - Comparison Between Lexicon and Statistical Approaches
  • 2021/12 - ことば工学研究会 優秀賞 論文の構造とタイトルを独立して考慮した医学論文検索モデルの提案
  • 2021/11 - 電気・情報関係学会北海道支部 若手優秀論文発表賞 BM25Tを用いたオンライン上の医療ニュース記事の根拠論文候補抽出
  • 2020 - WI2 Budding Research Award Mapping arguments to key point: Match Scoring of arguments using sentence embedding and MoverScore without labelled data
  • 2020 - WI2 Budding Research Award Unsupervised summarization of arguments toward key point generation with Sentence-BERT-based method
Show all
Association Membership(s) (6):
Association for Computational Linguistics (ACL) ,  AAAI ,  日本認知科学学会 ,  人工知能学会 ,  Japanese Cognitive Science Society ,  Japanese Society for Artificial Intelligence
※ Researcher’s information displayed in J-GLOBAL is based on the information registered in researchmap. For details, see here.

Return to Previous Page