Workshop on Language Technologies for Historical and Ancient Languages @ LREC 2026: all accepted papers
- A Dual-Modality Framework for Ancient Document Layout Analysis and Text RecognitionQi Fan, Jieming Hu, Chen Ye
- A Layered Annotation Workflow for Semitic EpigraphyTal Bernstein, Shai Gordin, Letizia Cerquegliniour summary
- A Multi-Modal Recognition Framework for Ancient Books Integrating DoRA-DPO Text Recognition and YOLO Layout AnalysisChaokun Zhang, Xin Wen, Tongtong Zhou
- A New State-of-the-Art BERT Model for Judeo-ArabicElisha Rosensweig, Yitzchak Lindenbaum, Hillel Gershuni et al.
- Across Generations: A Comparative Analysis of NER for Latin Inscriptions from Classical Machine Learning to LLMsWenhui Cui, Phillip Benjamin Ströbel
- AnandaSky: A Vision–Language Model for Line-Level Transcription of Historical Sinographic DocumentsColin Brisson, Ayoub Kahfy, Frédéric Constant et al.
- Automatic Detection of Metaphorical Expressions in Classical Japanese Using WLSP-Enhanced BERTHang Zhu, Mitoki Ohara, Rei Kikuchi et al.our summary
- BEReshiT: an Ancient Hebrew Model based on DictaBERTIglika Nikolova-Stoupak, Maxime Amblard, Frédérique Reyour summary
- Building Character(s): Synthetic Data and In-Context Learning Strategies for Few-Shot Ancient Chinese RecognitionDenise Atzori, Marie Bizais-Lillig, Mathias Garnier et al.
- Building a Corpus and Database for Rare and Undeciphered ScriptsBeata Megyesi, Rune Rattenborg, Benedek Láng et al.
- Capturing Ancient Chinese Sense Induction with Automatic PipelinesGuan-Yu Tseng, Chunki Lim, Chih-Han Lin et al.
- Classificatio Sine Iactu – That Is, Zero-Shot NERC in LatinLuisa Ripoll-Alberola, Fernando Nicolás-Flores, Francisco Javier Muñoz Acebes
- Contemporizing 20-th Century EstonianHeiki-Jaan Kaalep
- Contextual Probing for Low-Resource Named Entity Recognition in LatinMaria Mihaela Trusca, Mark Depauw, Violet Soen et al.our summary
- Cost-Aware Pre-Annotation Strategies for Nested NER in Historical Latin Notarial DeedsCharlene Ellul, Vanessa Buhagiar, Claudia Borg et al.
- Data-Centric Strategies for Ancient Chinese Text Recognition: Augmentation, Annotation Refinement, and Style Transfer in EvaHan 2026Li Chengfei, Zhang Yunjie, Li XiaoYi et al.
- Domain-Aware Error Correction for Citation NER in Medieval Hebrew ResponsaShmuel LIebeskind, Maayan Zhitomirsky-Geffet, Binyamin Katzoff et al.our summary
- Evaluating Hierarchical Aggregation and LLM-Based Matching for Synset Selection in Ancient GreekLuca Brigada Villa, Marco Passarotti, Chiara Zanchi et al.our summary
- Extending omnes flores for the EvaLatin 2026 Dependency Parsing TasksHiroshi Matsuda, Masayuki Asahara
- Extracting Volcanological Knowledge from Historical Texts: A Language-Technology Pipeline for Diachronic GeovisualizationCostanza Marini, Gianluca Casagrande, Alessio Palmero Aprosio et al.
- From Lemmas to Links: A Lemma Bank for Ancient GreekColin Swaelens, Francesco Mambrini, Marco Passarotti
- From Lemmatization to Legal Terminology: Assessing an Hybrid Pipeline on Justinian's DigestPaola Marongiu, Eva Sassoliniour summary
- From Manuscript to Model: Developing HTR for Medieval GreekNicklas Sindlev Andersen, Byron MacDougall, Tariq Yousef et al.
- I, RE:Claudius 256: Towards Linking Classical Latin Person Mentions to a Domain-specific Knowledge BaseMarijke Beersmans, Evelien de Graaf, Julie Nijs et al.
- LVLM Optimization for Ancient Chinese Book Image Analysis with Task-specific Augmentation and Instruction TuningTian Xia, Yulong Liu, Yilin Wang et al.
- Language Models for the Restoration of Latin Legal ManuscriptsShibingfeng Zhang, Edoardo Caraffa, Annafelicia Zuffrano et al.our summary
- Miktub: A Manuscript Dataset of Historical Maltese for Handwritten Text RecognitionThomas Koppens, Claudia Borg
- Morphological Annotation of Old Serbian in Universal DependenciesVladimir Polomac, Silvie Cinkova
- Multimodal Ancient Document Parsing: Technical Report for EvaHan2026 CompetitionLiqi He, Qiwei Li, Ziye Yang et al.
- Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient LanguagesNasma Chaoui, Richard Khoury
- OldBERTur: Named Entity Recognition for Medieval IcelandicPontus Henningsson, Eva Pettersson, Erik Lenas
- Overview of EvaHan2026: The First International Evaluation of Ancient Chinese OCR and Layout AnalysisDongbo Wang, Dongmei Zhu, Jieqiong Li et al.
- Overview of the Dependency Parsing Task at EvaLatin 2026Federica Iurescia, Marco Passarotti, Rachele Sprugnoli
- Overview of the Named Entity Recognition Task at EvaLatin 2026Valeria Irene Boano, Eleonora Litta, Matteo Romanello
- POS Tagging with Generative LLMs for Historical Germanic Low-Resource Languages: An Evaluation Against Fine-Tuned BERTIrene Miani, Gregory Darwin, Sara Stymne
- Pre-Editorial Normalization for Automatically Transcribed Medieval Manuscripts in Old French and LatinThibault Clérice, Rachel Bawden, Anthony Glaise et al.
- Smelling the Past: Investigating Historical Models for Olfactory Event ExtractionTeresa Paccosi, Marijn Koolen
- THIVLVC: Retrieval Augmented Dependency Parsing for LatinLuc Pommeret, Thibault Wagret, Jules Deretour summary
- The UD_Latin-PROIEL as Linked Open Data: Integrating a Latin Treebank into the LiLa Knowledge BaseLucas Consolin Dezotti, Marco Passarotti, Federica Iurescia et al.
- Tracing Morph Origins in Czech: A Computational Approach to Morph-Level EtymologyAleš Manuel Manuel Papáček, Zdeněk Žabokrtský
- Uncovering Work from Words: LLM-Based Information Extraction from Historical PetitionsEllinor Lindqvist, Eva Pettersson, Joakim Nivre
- UppsalaNLP at EvaLatin 2026: Multilingual parsing for LatinSara Stymneour summary
- When Lexicographic Quotations Become a Corpus: To Deduplicate or Not to Deduplicate?Manuel Favaro, Elisa Guadagnini, Eva Sassolini et al.
This page in Markdown → https://md.research.elamur.ai/free/en/venues/lt4hala/2026/papers/