Accepted papers

Research papers

• Irish-based Large Language Model with Extreme Low-Resource Settings in Machine Translation

• Rosetta Balcanica: Deriving a "Gold Standard''  Neural Machine Translation (NMT) Parallel Dataset from High-Fidelity Resources for Western Balkan Languages

• Benchmarking of Low-Resource Machine Translation Systems

• Finetuning End-to-End Models for  Estonian Conversational Spoken Language Translation

• Tuning LLMs with Contrastive Alignment Instructions for Machine Translation in Unseen, Low-resource Languages

• Learning-From-Mistakes Prompting for Indigenous Language Translation

• AGE: Amharic, Ge’ez and English Parallel Dataset

• Rule-Based, Neural and LLM Back-Translation: Comparative Insights from a Variant of Ladin

• Machine Translation Through Cultural Texts: Can Verses and Prose Help Low-Resource Indigenous Models?

• Tokenisation in Machine Translation Does Matter: The impact of different tokenisation approaches for Maltese

• Super donors and super recipients: Studying cross-lingual transfer between high-resource and low-resource languages

• Leveraging Mandarin as a Pivot Language for Low-Resource Machine Translation from Cantonese to English

• Enhancing Low-Resource NMT with a Multilingual Encoder and Knowledge Distillation: A Case Study

• Linguistically Informed Transformers for Text to American Sign Language Translation

• KpopMT: Translation Dataset with Terminology for Kpop Fandom

• Challenges in Urdu Machine Translation

• Enhancing Turkish Word Segmentation: A Focus on Borrowed Words and Invalid Morpheme

• Adopting Ensemble Learning for Cross-lingual Classification of Crisis-related Text On Social Media

• HeSum: a Novel Dataset for Abstractive Text Summarization in Hebrew

• Low-Resource Cross-Lingual Summarization through Few-Shot Learning with Large Language Models