9 papers
Expanding the Lexicon of Ge'ez Based African Languages: A Comparative Study of Amharic and Tigrinya
Hailay Kidu Teklehaymanot, Debela Desalegn Yadeta, Wolfgang Nejdl
Multilingual pre-trained language models such as XLM-R perform well for major languages but struggle with low-resource Ge'ez-script languages, largely because Latin-script-centric…
LLM Probe: Evaluating LLMs for Low-Resource Languages
Hailay Kidu Teklehaymanot, Gebrearegawi Gebremariam, Wolfgang Nejdl
Despite rapid advances in large language models (LLMs), their linguistic abilities in low-resource and morphologically rich languages are still not well understood due to limited a…
LGSE: Lexically Grounded Subword Embedding Initialization for Low-Resource Language Adaptation
Hailay Teklehaymanot, Dren Fazlija, Wolfgang Nejdl
Adapting pretrained language models to low-resource, morphologically rich languages remains a significant challenge. Existing vocabulary expansion methods typically rely on arbitra…
Tokenization Disparities as Infrastructure Bias: How Subword Systems Create Inequities in LLM Access and Efficiency
Hailay Kidu Teklehaymanot, Wolfgang Nejdl
Tokenization disparities pose a significant barrier to achieving equitable access to artificial intelligence across linguistically diverse populations. This study conducts a large-…
Morphological Synthesizer for Ge'ez Language: Addressing Morphological Complexity and Resource Limitations
Gebrearegawi Gebremariam, Hailay Teklehaymanot, Gebregewergs Mezgebe
Ge'ez is an ancient Semitic language renowned for its unique alphabet. It serves as the script for numerous languages, including Tigrinya and Amharic, and played a pivotal role in…
Low-Resource English-Tigrinya MT: Leveraging Multilingual Models, Custom Tokenizers, and Clean Evaluation Benchmarks
Hailay Kidu Teklehaymanot, Gebrearegawi Gidey, Wolfgang Nejdl
Despite advances in Neural Machine Translation (NMT), low-resource languages like Tigrinya remain underserved due to persistent challenges, including limited corpora, inadequate to…
MoVoC: Morphology-Aware Subword Construction for Geez Script Languages Corrected version
Hailay Kidu Teklehaymanot, Dren Fazlija, Wolfgang Nejdl
Subword-based tokenization methods often fail to preserve morphological boundaries, a limitation especially pronounced in low-resource, morphologically complex languages such as th…
RAGtifier: Evaluating RAG Generation Approaches of State-of-the-Art RAG Systems for the SIGIR LiveRAG Competition
Tim Cofala, Oleh Astappiev, William Xion +1
Retrieval-Augmented Generation (RAG) enriches Large Language Models (LLMs) by combining their internal, parametric knowledge with external, non-parametric sources, with the goal of…
TIGQA:An Expert Annotated Question Answering Dataset in Tigrinya
Hailay Teklehaymanot, Dren Fazlija, Niloy Ganguly +2
The absence of explicitly tailored, accessible annotated datasets for educational purposes presents a notable obstacle for NLP tasks in languages with limited resources.This study…