[INDOLOGY] Workshop "OCR AND BEYOND: Doing Philology, Building Structured Corpora, and Computer-aided Annotation Workflows in the Age of Generative AI*

[Sebastian Nehrdich]

Dear List members,

This is to draw your attention to a small event we are hosting here at
Tohoku University in Sendai, on the coming weekend, and online
participation is possible as well!

OCR AND BEYOND
Doing Philology, Building Structured Corpora, and Computer-aided
Annotation Workflows in the Age of Generative AI

Date:
March 28-29

Location:
Tohoku University
Katahira Campus
WPI-AIMR Main Building (B01)
Seminar Room, 2nd floor


Time zone:
JST

Registration for online participation:
https://docs.google.com/forms/d/e/1FAIpQLSc9NCF13PFBXLxN56b_KrhUzc7_xjvyQosNoUmfnjN0jUErNQ/viewform

Program

Saturday, March 28

10:00-10:05
Opening: Welcome


10:05-10:35
On Reading Śāstra with Claude: Practical Reflections on AI in Sanskrit Studies
Kei Kataoka

10:35-11:05
Indological Research in 2026: How AI is Helping, with Various Examples
Kengo Harimoto

11:05-11:35
“They build a hut for the sacrificer”:
Towards a Word-aligned Corpus of Vedic Prose
Oliver Hellwig

11:35-12:20
Discussion on Session 1 Themes
Lead: Kyoko Amano

12:20-13:20
Lunch

13:20-13:50
The Vedic Prose Corpus: Progress, Challenges, Visions
Sven Sellmer

13:50-14:20
eText Collections, Repositories, and Distribution:
Observations towards Quality Control
Julian Schott

14:20-14:50
Towards a Sustainable Dataset of Colophons, Paratexts, and Inscriptions
Ryan Conlon

14:50-15:35
Discussion on Session 2 Themes
Lead: Kengo Harimoto

15:35
Closing

Sunday, March 29

10:30-11:00
HTR for Nepalese Manuscripts in Pracalit Script
Alexander J. O’Neill

11:00-11:30
Who Is Speaking? Encoding and Detecting Quotation Layers in Japanese
Esoteric Buddhist Texts
Gaetan Rappo

11:30-12:00
Discussion on Session 3 Themes
Lead: Oliver Hellwig, Sven Sellmer

12:00-13:00
Lunch

13:00-13:30
A Preliminary Investigation of OCR Techniques for Tibetan Materials
Preserved at Tohoku University
Ryuta Kikuya

13:30-14:00
Seeing the Full Elephant: Vision Language Model and LLM Use at the
Dharmamitra Project
Sebastian Nehrdich

14:00-14:15
The Significance of Buddhist Studies in East Asian/Japanese Text Encoding
Kiyonori Nagasaki

14:15-15:00
Discussion on Session 4 Themes
Lead: Oliver Hellwig, Sven Sellmer

15:00
Closing



--
Sebastian Nehrdich

Distinguished Assistant Professor
Tohoku University
Center for Integrated Japanese Studies

東北大学 合日本学センター
ディスティングイッシュトアシスタントプロフェッサー（助教）

〒980-8576
https://cijs.oii.tohoku.ac.jp/
sebastian-nehrdich.com
✉️ nehrdich at tohoku.ac.jp
☎️ 022-795-3822