研究者詳細

顔写真

ニアデイツヒ　セバスチヤン
Nehrdich Sebastian
Nehrdich Sebastian
所属
国際連携推進機構　統合日本学センター
職名
助教
学位

  • Doctor of Philosophy (PhD) （Heinrich-Heine-Universität Düsseldorf (University of Duesseldorf)）

e-Rad 研究者番号
11034744
プロフィール

I am an Assistant Professor working on Natural Language Processing and Digital Humanities at the Center for Integrated Japanese Studies, Tohoku University. My interests are machine learning and natural language processing with special focus on Asian low-resource languages as well as the intersection between Buddhist Studies and NLP applications. In 2025, I completed my PhD in computational linguistics at University of Duesseldorf, under the guidance of Oliver Hellwig and Kurt Keutzer. I have completed a bachelor's degree in Indology and Sinology (2017) and a master's degree in Buddhist Studies (2020) at University of Hamburg.

Since 2023, I am part of the Dharmamitra project, first as CTO and now as director in collaboration with co-founder Kurt Keutzer at Berkeley AI Research Lab (BAIR), UC Berkeley. In this project, we develop machine translation models as well as semantic search functionality, parallel passage detection, and OCR for Classical Asian languages.

Since 2018, I am working on the NLP technology and database system of the BuddhaNexus platform for the research of intertextual links within Buddhist sources, which is now continued as DharmaNexus.

 

経歴 3

  • 2025年10月 ～ 継続中
    東北大学　統合日本学センター　助教

  • 2023年4月 ～ 2025年9月
    University of California, Berkeley　Berkeley AI Research Lab　Researcher

  • 2021年3月 ～ 2023年3月
    Heinrich-Heine University, Duesseldorf　Institut fuer Linguistik　Researcher

学歴 3

  • University of Duesseldorf (Heinrich-Heine-Universität Düsseldorf)　Computational Linguistics　PhD

    2020年 ～ 2025年

  • University of Hamburg　Buddhist Studies　Master of Arts (MA)

    2017年 ～ 2020年

  • University of Hamburg　Indology (major), Sinology (minor)　Bachelor of Arts (BA)

    2012年 ～ 2017年

研究キーワード 9

  • Pāli

  • Japanese NLP

  • Machine Translation

  • Informational Retrieval

  • Sanskrit

  • Optical Character Recognition (OCR)

  • Classical Chinese

  • Tibetan

  • Natural Language Processing

研究分野 4

  • 人文・社会 / 言語学 /

  • 人文・社会 / 中国哲学、印度哲学、仏教学 /

  • 人文・社会 / 図書館情報学、人文社会情報学 /

  • 情報通信 / 知能情報学 /

受賞 3

  1. Best Dissertation of the Year 2025 (Beste Dissertation des Jahres 2025)

    2025年　Faculty of Arts and Humanities, University of Düsseldorf　Development of a Computational Framework for the Intertextual Analysis of Indian Abhidharma and Yogācāra Literature

  2. Khyentse Foundation Award for Excellence in Buddhist Studies

    2020年　Khyentse Foundation and the Department of Indian and Tibetan Studies, Universität Hamburg

  3. Scholarship for bachelor and master degree (2015–2020)

    2015年　German Academic Scholarship Foundation (Studienstiftung des deutschen Volkes)

論文 12

  1. Sanskrit Word Sense Disambiguation Based on Lexicographic Definitions 査読有り

    Oliver Hellwig, Sven Sellmer, Sebastian Nehrdich, Paul Widmer, Rico Sennrich

    Proceedings of the 8th International Sanskrit Computational Linguistics Symposium　2026年

  2. MITRA-zh-eval: Using a Buddhist Chinese Language Evaluation Dataset to Assess Machine Translation and Evaluation Metrics 査読有り

    Sebastian Nehrdich, Avery Chen, Marcus Bingenheimer, Lu Huang, Rouying Tang, Xiang Wei, Leijie Zhu, Kurt Keutzer

    Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities　129-137　2025年

  3. Breakthroughs in Tibetan NLP & Digital Humanities 査読有り

    Marieke Meelen, Sebastian Nehrdich, Kurt Keutzer

    Revue d'Etudes Tibétaines　72　5-25　2024年

  4. One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks 査読有り

    Sebastian Nehrdich, Oliver Hellwig, Kurt Keutzer

    Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (Findings)　2024年

  5. Observations on the Intertextuality of Selected Abhidharma Texts Preserved in Chinese Translation 査読有り

    Sebastian Nehrdich

    Religions　14　(7)　911　2023年

  6. MITRA-zh: An efficient, open machine translation solution for Buddhist Chinese 査読有り

    Sebastian Nehrdich, Marcus Bingenheimer, Justin Brody, Kurt Keutzer

    NLP4DH　2023年

  7. Data-driven dependency parsing of Vedic Sanskrit 査読有り

    Oliver Hellwig, Sebastian Nehrdich, Sven Sellmer

    Language Resources and Evaluation　57　1173-1206　2023年

  8. SansTib, a Sanskrit - Tibetan Parallel Corpus and Bilingual Sentence Embedding Model 査読有り

    Sebastian Nehrdich

    Proceedings of the 13th Conference on Language Resources and Evaluation, LREC 2022　6728-6734　2022年

  9. Accurate Dependency Parsing and Tagging of Latin 査読有り

    Sebastian Nehrdich, Oliver Hellwig

    Proceedings of the Second Workshop on Language Technologies for Historical and Ancient Languages, LT4HALA 2022　20-25　2022年

  10. Obtaining More Expressive Corpus Distributions for Standardized Ancient Languages 査読有り

    Oliver Hellwig, Sven Sellmer, Sebastian Nehrdich

    Proceedings of the Conference on Computational Humanities Research, CHR2021　92-107　2021年

  11. A Method for the Calculation of Parallel Passages for Buddhist Chinese Sources Based on Million-scale Nearest Neighbor Search

    Sebastian Nehrdich

    Journal of the Japanese Association of the Digital Humanities　5　2020年

  12. Sanskrit Word Segmentation Using Character-level Recurrent and Convolutional Neural Networks 査読有り

    Oliver Hellwig, Sebastian Nehrdich

    Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing　2754-2763　2018年

︎全件表示 ︎最初の5件までを表示

講演・口頭発表等 44

  1. Access as Nonviolence: Designing DH Platforms That Reduce Inequality

    Sebastian Nehrdich

    Ahimṣā Lecture Series, Asia-Africa Institute, University of Hamburg, Hamburg, Germany　2026年5月

  2. Artificial Intelligence in Buddhist Studies 招待有り

    Sebastian Nehrdich

    Workshop in Leipzig, Leipzig, Germany　2026年5月

  3. Dharmamitra in 2026: Current Capabilities and Future Developments

    Sebastian Nehrdich

    Talk, Institute for Indology and Tibetology, Ludwig-Maximilians-Universität München, Munich, Germany　2026年5月

  4. Is This the End of (Buddhist) Philology as We Know It? If So, What's Next? 招待有り

    Sebastian Nehrdich

    International Institute for Asian Studies, Leiden University, Leiden, Netherlands　2026年3月

  5. DharmaNexus as a Multilingual Graph of Buddhist Intertextuality: Design Choices, Research Uses, and Future Applications 招待有り

    Sebastian Nehrdich

    Gandhāra Corpora Lecture Series, Ghent Centre for Buddhist Studies, Ghent University, Ghent, Belgium　2026年3月

  6. Dharmamitra: A Platform to Support Research across Language Boundaries on Buddhist Textual Material

    Sebastian Nehrdich

    Workshop: Japanese Studies in Japan and Belgium, Faculty of Arts and Philosophy, Ghent University, Ghent, Belgium　2026年3月

  7. OCR and Beyond: Philology and Digital Archives in the Age of AI

    Sebastian Nehrdich

    Workshop, Center for Integrated Japanese Studies (CIJS), Tohoku University, Sendai, Japan　2026年3月

  8. AI and Indological/Buddhological Researches: Dharmamitra/DharmaNexus and Its Application

    Sebastian Nehrdich, Kengo Harimoto

    32nd Annual Conference of the Association for the Study of the History of Indian Thought, Faculty of Letters, Kyoto University, Kyoto, Japan　2026年1月

  9. Dharmamitra: A Data-Driven Platform for the Research of Buddhist Texts in Multiple Languages Using Advanced NLP Methods 招待有り

    Sebastian Nehrdich

    30th Information and Knowledge Science Forum, Doshisha University Osaka Satellite Campus, Osaka, Japan　2026年1月

  10. Building the Foundations of Buddhist Philology through Digital Humanities: Exploring the Potential of the Tohoku University Digital Archives (ToUDA)

    Sebastian Nehrdich

    Workshop and Symposium, Center for Integrated Japanese Studies (CIJS), Tohoku University, Sendai, Japan　2025年12月

  11. Dharmamitra: A Platform that Makes Translation and Discovery of Buddhist Texts Possible Across Language Barriers

    Sebastian Nehrdich

    11th Symposium of Humanistic Buddhism, Taiwan　2025年12月

  12. Translation, OCR, and Semantic Retrieval: Current Status and Future Outlook of the Dharmamitra Ecosystem 招待有り

    Sebastian Nehrdich

    Buddhist Studies and Digital Humanities International Symposium, Tokyo International Forum, Tokyo, Japan　2025年12月

  13. From OCR via Machine Translation to Semantic Search: The Dharmamitra AI Stack for Multilingual Buddhist Philology 招待有り

    Sebastian Nehrdich

    Seoul National University AI Digital Humanities Center Overseas Researcher Invitation Forum, Seoul, South Korea　2025年11月

  14. Buddhist Philology and AI 招待有り

    Sebastian Nehrdich

    Goodman Lecture Series, Khyentse Foundation, Online　2025年10月

  15. Dharmamitra & DharmaNexus: A New Set of Digital Tools for the Study of Buddhist Texts

    Sebastian Nehrdich

    Workshop: Decoding Buddhist Text Wisdom, Institute of Chinese Literature and Philosophy, Academia Sinica, Taipei, Taiwan　2025年9月

  16. Digital Humanities and Buddhist Language Resources: New Possibilities for Reading the Classics 招待有り

    Sebastian Nehrdich

    Invited Talk, National Taiwan University, Taipei, Taiwan　2025年9月

  17. MITRA: New Research Tools for a Paradigm Shift in the Philological Study of Buddhist Texts Based on Machine Translation Technology

    Sebastian Nehrdich

    Panel: Machine Translation, Large Language Models, and Buddhist Studies, XXth Congress of the International Association of Buddhist Studies　2025年8月

  18. Dharmamitra & DharmaNexus: A New Set of Digital Tools for the Philological Study of Buddhist Texts 招待有り

    Sebastian Nehrdich

    Invited Talk, ELTE BTK, Budapest, Hungary　2025年8月

  19. From Sthiramati to Dharmamitra: Developing Digital Tools for a New Age of Philological Buddhist Studies 招待有り

    Sebastian Nehrdich

    DH International Workshop, Keio University, Tokyo, Japan　2025年6月

  20. Is training deep neural embeddings worth the effort? A preliminary investigation of different representation methods for semantic similarity tasks in Buddhist Chinese and related languages

    Sebastian Nehrdich

    Online Workshop: Navigating Indra's Net - Digital Approaches to Text Reuse-based Intertextuality in Pre-Modern East Asian Texts, Hanmun Lab, Ruhr-Universität Bochum, Germany (online)　2025年6月

  21. MITRASearch: Building Information Retrieval Systems for Classical Asian Languages in the Age of AI

    Sebastian Nehrdich

    CEAL Technology Forum, Council on East Asian Libraries, Columbus, Ohio, USA　2025年3月

  22. Machine Translation for Asian Studies

    Sebastian Nehrdich

    Workshop, Annual Conference of the Association of Asian Studies, Columbus, Ohio, USA　2025年3月

  23. MITRA Search: Exploring Buddhist Literature Preserved in Classical Asian Languages with Multilingual Approximate Search 招待有り

    Sebastian Nehrdich

    International Symposium: Buddhist Studies and Digital Humanities: 100 Years of the Taishō Tripiṭaka and 30 Years of SAT, University of Tokyo, Japan　2024年12月

  24. Dharmamitra: New Tools for Sanskrit Translation, Grammatical Analysis, Search, and Digital Philology 招待有り

    Sebastian Nehrdich

    Manuscriptology and Digital Humanities Online Lecture Series, Heidelberg University and Otani University　2024年11月

  25. Dharmamitra: Developing a Toolkit for Philological Work on Premodern Asian Low-Resource Languages

    Sebastian Nehrdich

    Workshop: Case Studies - Conversations on Digital Scholarly Editing, Sivadharma Project, University of Naples L'Orientale, Naples, Italy　2024年11月

  26. Dharmamitra Search: Leveraging Multilingual Language Models for Search and Detection of Textual Reuse across Diverse Text Collections 招待有り

    Sebastian Nehrdich

    Conference: AI and the Future of Buddhist Studies, Numata Center for Buddhist Studies, University of California Berkeley, USA　2024年10月

  27. MITRA: Beyond Just Machine Translation for Premodern Asian Low Resource Languages 招待有り

    Sebastian Nehrdich

    Invited Seminar Talk, Center for Language and Speech Processing, Johns Hopkins University, Baltimore, USA　2024年10月

  28. MITRA: Developing Language Models for Machine Translation and Search in Buddhist Source Languages

    Sebastian Nehrdich

    PNC Annual Conference and Joint Meetings, Seoul, South Korea　2024年8月

  29. Massive Multilingual Machine Translation and Search for Buddhist Languages: The MITRA Project 招待有り

    Sebastian Nehrdich

    International Conference on Retrospect and Prospect of Digitalization of Buddhist Resources, National Taiwan University, Taipei, Taiwan　2024年4月

  30. Dharmamitra: Enabling Massive Multilingual Machine Translation for Ancient Languages of the Buddhist Tradition 招待有り

    Sebastian Nehrdich

    Interdisciplinary Symposium on Machine Translation and Digital Humanities, National University of Singapore, Singapore　2024年3月

  31. Machine Translation and LLM-Powered Grammatical Explanation for Sanskrit

    Sebastian Nehrdich

    International Sanskrit Computational Linguistics Conference, Auroville, India　2024年2月

  32. Developing Machine Translation for Ancient Buddhist Texts in Canonical Languages 招待有り

    Sebastian Nehrdich

    Invited Workshop: Machine Translation and Algorithmic Study of Classical Buddhist Texts, Dongguk University, Seoul, South Korea　2023年6月

  33. MITRA: Developing Natural Language Processing Tools for the Languages of Buddhist Literature 招待有り

    Sebastian Nehrdich

    International Symposium: Maitreya Faith/Philosophy and Buddhist Community Service, Chinese University of Hong Kong, Hong Kong　2023年6月

  34. Creating a Shared Semantic Vector Space for Buddhist Languages 招待有り

    Sebastian Nehrdich

    Invited Talk, Symposium: Advanced Computational Methods for Studying Buddhist Texts, Institute for the Cultural and Intellectual History of Asia, Austrian Academy of Sciences, Vienna, Austria　2023年4月

  35. Multilingual Semantic Mining for Text Alignment and Parallel Corpus Building for Buddhist Languages

    Sebastian Nehrdich

    International Symposium: Perspectives of Digital Humanities in the Field of Buddhist Studies, Universität Hamburg, Hamburg, Germany　2023年1月

  36. ChronBMM - Dating Text Corpora Using Bayesian Mixture Models

    Sebastian Nehrdich

    International Symposium: Perspectives of Digital Humanities in the Field of Buddhist Studies, Universität Hamburg, Hamburg, Germany　2023年1月

  37. The Uncertain Future of Buddhist (Machine) Translation

    Sebastian Nehrdich

    PNC Annual Conference and Joint Meetings, University of Arizona, Tucson, USA　2022年9月

  38. ChronBMM: Bayesian Mixture Models für die Datierung von Textkorpora

    Sebastian Nehrdich

    Deutscher Orientalistentag (DOT) 2022, Freie Universität Berlin, Berlin, Germany　2022年9月

  39. Current State of the BuddhaNexus, a Powerful Database for Research on Buddhist Corpora

    Sebastian Nehrdich

    16th Seminar of the International Association for Tibetan Studies, Prague, Czech Republic　2022年7月

  40. Machine Translation and Buddhist Studies - First Results

    Sebastian Nehrdich

    Digital Orientalist Online Conference: Infrastructure　2022年6月

  41. Observations on the Intertextual Relationship of the Sarvāstivāda Abhidharma Literature Preserved in Chinese Translation 招待有り

    Sebastian Nehrdich

    Khyentse Lecture Series, Universität Hamburg, Hamburg, Germany　2022年4月

  42. Observations on the Intertextual Relationship and Possible Authorship of the Abhidharma and Yogācāra Works Attributed to Vasubandhu

    Sebastian Nehrdich

    Workshop: Buddhism and Language: A Twofold Perspective, Ludwig-Maximilians-Universität München, Munich, Germany　2021年10月

  43. Towards a New Edition of the Fourth Chapter of the Madhyāntavibhāgaṭīkā by Sthiramati 招待有り

    Sebastian Nehrdich

    Young Scholars Workshop, University of Tsukuba, Tsukuba, Japan　2018年9月

  44. Perspectives on Building a Multilingual Parallel Corpus of Ancient Buddhist Scriptures Based on Machine Learning 招待有り

    Sebastian Nehrdich

    Exzellenzcluster 'Asien und Europa im globalen Kontext', Universität Heidelberg, Heidelberg, Germany　2018年6月

︎全件表示 ︎最初の5件までを表示

共同研究・競争的資金等の研究課題 2

  1. Connectivity and Individuality in Textual Traditions: Augmenting Retrieval for Eurasian Languages

    Sebastian Nehrdich

    提供機関：Schmidt Sciences

    制度名：Humanities and AI Virtual Institute (HAVI)

    研究機関：Tohoku University

    2025年12月 ～

  2. Google Cloud Research Credits Grant for Cultural Preservation Tasks at the Dharmamitra Project

    Sebastian Nehrdich

    提供機関：Google

    制度名：Google Cloud Research Credits Program

    研究機関：Tohoku University

    2024年 ～