May 4, 2025
9:00 - 9:05: Opening Remarks
9:05 - 9:35: Invited Talks
The Role of “Small” Models for Ancient NLP in a World of Large Language Models
9:35 - 10:35: Oral Reports A (Part 1)
Automatic Text Segmentation of Ancient and Historic Hebrew
Integrating Semantic and Statistical Features for Authorial Clustering of Qumran Scrolls
Assignment of account type to proto-cuneiform economic texts with Multi-Class Support Vector Machines
Accessible Sanskrit: A Cascading System for Text Analysis and Dictionary Access
10:35 - 10:55: Break
10:55 - 11:10: Oral Reports A (Part 2)
A Dataset of Ancient Chinese Math Word Problems and an Application for Research in Historic Mathematics
11:10 - 11:45: Poster
Using Cross-Linguistic Data Formats to Enhance the Annotation of Ancient Chinese Documents Written on Bamboo Slips
Towards an Integrated Methodology of Dating Biblical Texts: The Case of the Book of Jeremiah
The Development of Hebrew in Antiquity – A Computational Linguistic Study
Evaluating Evaluation Metrics for Ancient Chinese to English Machine Translation
Neural Models for Lemmatization and POS-Tagging of Earlier and Late Egyptian (Supporting Hieroglyphic Input) and Demotic
Bringing Suzhou Numerals into the Digital Age: A Dataset and Recognition Study on Ancient Chinese Trade Records
The Historian’s Fingerprint: Computational Stylometric Analysis of the Zuo Com-mentary and Discourses of the States
11:50 - 13:30: Lunch
13:30 - 14:00: Invited Talks
Ancient languages in the age of LLMs: opportunities and challenges
14:00 - 15:30: EvaHan
Opening and Invited Talk
Overview of EvaHan2025: The First International Evaluation on Ancient Chinese Named Entity Recognition
Exploring the Application of 7B LLMs for Named Entity Recognition in Chinese Ancient Texts
Construction of NER Model in Ancient Chinese: Solution of EvaHan 2025 Chal-lenge
LLM’s Weakness in NER Doesn’t Stop It from Enhancing a Stronger SLM
Named Entity Recognition in Context: Edit_Dunhuang team Technical Report for Evahan2025 NER Competition
Simple Named Entity Recognition (NER) System with RoBERTa for Ancient Chinese
Make Good Use of GujiRoBERTa to Identify Entities in Ancient Chinese
GRoWE: A GujiRoBERTa-Enhanced Approach to Ancient Chinese NER via Word-Word Relation Classification and Model Ensembling
When Less Is More: Logits-Constrained Framework with RoBERTa for Ancient Chi-nese NER
15:30 - 15:50: Break
15:50 - 16:30: EvaCun
EvaCun 2025 Shared Task: Lemmatization and Token Prediction in Akkadian and Sumerian using LLMs
Lemmatization of Cuneiform Languages Using the ByT5 Model
Finetuning LLMs for EvaCun 2025 token prediction shared task
Beyond Base Predictors: Using LLMs to Resolve Ambiguities in Akkadian Lemma-tization
A Low-Shot Prompting Approach to Lemmatization in the EvaCun 2025 Shared Task
16:30 - 17:45: Oral Reports B
From Clay to Code: Transforming Hittite Texts for Machine Learning
Towards Ancient Meroitic Decipherment: A Computational Approach
Detecting Honkadori based on Waka Embeddings
Incorporating Lexicon-Aligned Prompting in Large Language Model for Tangut–Chinese Translation
ParsiPy: NLP Toolkit for Historical Persian Texts in Python
17:45 - 17:50: Awards, Open Discussion and Closing