From the archive
Week 3417 – 23 Aug 20267 papers
Multilingual LLM judges produce different evaluator-backbone rankings depending on the prompt language: on an eight-language Agent-as-a-Judge benchmark, the top-ranked backbone alternates across English, Arabic, Chinese, Hindi, Japanese, Spanish, Turkish, and …
One of the basic Natural Language Processing (NLP) tasks is Part-of-Speech (POS) tagging, which helps in various applications like sentiment analysis and information retrieval. However, creating accurate POS taggers for low-resource African languages continues…
Language is a critical determinant of health equity in South Africa’s multilingual healthcare system. Despite constitutional mandates to communicate in indigenous languages such as isiXhosa, many public health materials remain inadequately translated, compromi…
The rapid progress in Artificial Intelligence has largely bypassed African languages, creating a digital divide that limits AI adoption on the continent. Recent open-source LLMs systematically underperform on African language machine translation, while the lac…
This study introduces a novel, publicly available balanced Algerian Arabic Aspect Based Sentiment Analysis (ABSA) dataset consisting of 11,338 comments written in the Algerian dialect. The dataset follows the semantic evaluation 2016 annotation guidelines and …
We ask whether internal representation statistics can provide useful example-level difficulty signals for adaptive inference in multilingual African NLP, and find that they cannot in this setting. Studying natural language inference across 15 African languages…
This study is on the forms and functions of interrogative markers in Fulfulde. It aims at providing a clear view of interrogative markers and their functions in Fulfulde sentences. Specifically, to determine: the forms, functions and the syntactic constraints …
One email each Monday with the week's new African NLP papers. Double opt-in, unsubscribe any time.