5 papers
Global PIQA: Evaluating Commonsense Reasoning Across 100+ Languages and Cultures
Tyler A. Chang, Catherine Arnett, Abdelrahman Sadallah +377
To date, there exist almost no culturally-specific evaluation benchmarks for large language models (LLMs) that cover a large number of languages and cultures. In this paper, we pre…
NSL-MT: Linguistically Informed Negative Samples for Efficient Machine Translation in Low-Resource Languages
Mamadou K. Keita, Christopher Homan, Huy Le
We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated…
InstructLR: A Scalable Approach to Create Instruction Dataset for Under-Resourced Languages
Mamadou K. Keita, Sebastien Diarra, Christopher Homan +1
Effective text generation and chat interfaces for low-resource languages (LRLs) remain a challenge for state-of-the-art large language models (LLMs) to support. This is mainly due…
Grammatical Error Correction for Low-Resource Languages: The Case of Zarma
Mamadou K. Keita, Adwoa Bremang, Huy Le +3
Grammatical error correction (GEC) aims to improve text quality and readability. Previous work on the task focused primarily on high-resource languages, while low-resource language…
R2T: Rule-Encoded Loss Functions for Low-Resource Sequence Tagging
Mamadou K. Keita, Christopher Homan, Sebastien Diarra
We introduce the Rule-to-Tag (R2T) framework, a hybrid approach that integrates a multi-tiered system of linguistic rules directly into a neural network's training objective. R2T's…