Word Error Rate (WER) mischaracterizes ASR models' performance for African languages by combining phonological, tone, and other linguistic errors into a single lexical error. By contrast, Feature Error Rate (FER) has recently attracted attention as a viable metric that reveals linguistically meaningful errors in models' performance. In this paper, we evaluate three speech encoders on two African languages by complementing WER with CER, and FER, and add a tone-aware extension (TER). We show that by computing errors on phonological features, FER and TER reveal linguistically-salient error patterns even when word-level accuracy remains low. Our results reveal that models perform better on segmental features, while tones (especially mid and downstep) remain the most challenging features. Results on Yoruba show a striking differential in metrics, with WER=0.788, CER=0.305, and FER=0.151. Similarly for Uneme (an endangered language absent from pretraining data) a model with near-total WER and 0.461 CER achieves the relatively low FER of 0.267. This indicates model error is often attributable to individual phonetic feature errors, which is obscured by all-or-nothing metrics like WER.
Safety alignment in large language models relies predominantly on English-language training data. When harmful intent is expressed in low-resource languages, refusal mechanisms that hold in English frequently fail to activate. We introduce LSR (Linguistic Safety Robustness), the first systematic benchmark for measuring cross-lingual refusal degradation in West African languages: Yoruba, Hausa, Igbo, and Igala. LSR uses a dual-probe evaluation protocol - submitting matched English and target-language probes to the same model - and introduces Refusal Centroid Drift (RCD), a metric that quantifies how much of a model's English refusal behavior is lost when harmful intent is encoded in a target language. We evaluate Gemini 2.5 Flash across 14 culturally grounded attack probes in four harm categories. English refusal rates hold at approximately 90 percent. Across West African languages, refusal rates fall to 35-55 percent, with Igala showing the most severe degradation (RCD = 0.55). LSR is implemented in the Inspect AI evaluation framework and is available as a PR-ready contribution to the UK AISI's inspect_evals repository. A live reference implementation and the benchmark dataset are publicly available.
This article argues that So Long a Letter (1979) constructs African female subjectivity as a dialogical self forged through the confessional epistle’s denouncement of colonial and patriarchal forces that have long sought to bend African women’s heads to external and internal orderings of their society. It contends that Bâ carves temporal and narrative spaces for African women by casting a subversive gaze on the interlocking systems of oppression that repress their sense of agency. Through the enabling potential of epistolary writing, the Senegalese writer fashions her heroine into a subjectivity that is neither given nor fixed, but constructed in the shifting positions of friend, wife, mother, widow, and at times Bâ’s own mouthpiece, and through a continuing dialogue with past memories, present dilemmas, and alternative temporalities beyond dominant chrononorms. Drawing on Bakhtinian dialogism, Anzaldúa’s mestiza consciousness, Freeman’s chrononormativity, and Barrett’s affective continuum, this analysis therefore seeks to offer a transdisciplinary investigation into the ways how the novel reimagines African female subjectivity as a dialogic process of becoming emanating from the interstices of epistolary voice, affective temporalities, and the repudiation of colonial and patriarchal chrononormative imperatives. Ultimately, the paper concludes that the novel becomes a canvas onto which Bâ inscribes alternative modes of self-articulation, collective agency, and female futurity for African women.
History of Africa, African languages and literature
Compilers play a central role in translating high-level code into executable programs, making their correctness essential for ensuring code safety and reliability. While extensive research has focused on verifying the correctness of compilers for single-language compilation, the correctness of cross-language compilation - which involves the interaction between two languages and their respective compilers - remains largely unexplored. To fill this research gap, we propose CrossLangFuzzer, a novel framework that introduces a universal intermediate representation (IR) for JVM-based languages and automatically generates cross-language test programs with diverse type parameters and complex inheritance structures. After generating the initial IR, CrossLangFuzzer applies three mutation techniques - LangShuffler, FunctionRemoval, and TypeChanger - to enhance program diversity. By evaluating both the original and mutated programs across multiple compiler versions, CrossLangFuzzer successfully uncovered 10 confirmed bugs in the Kotlin compiler, 4 confirmed bugs in the Groovy compiler, 7 confirmed bugs in the Scala 3 compiler, 2 confirmed bugs in the Scala 2 compiler, and 1 confirmed bug in the Java compiler. Among all mutators, TypeChanger is the most effective, detecting 11 of the 24 compiler bugs. Furthermore, we analyze the symptoms and root causes of cross-compilation bugs, examining the respective responsibilities of language compilers when incorrect behavior occurs during cross-language compilation. To the best of our knowledge, this is the firstwork specifically focused on identifying and diagnosing compiler bugs in cross-language compilation scenarios. Our research helps to understand these challenges and contributes to improving compiler correctness in multi-language environments.
Sukairaj Hafiz Imam, Babangida Sani, Dawit Ketema Gete
et al.
Automatic Speech Recognition (ASR) technologies have transformed human-computer interaction; however, low-resource languages in Africa remain significantly underrepresented in both research and practical applications. This study investigates the major challenges hindering the development of ASR systems for these languages, which include data scarcity, linguistic complexity, limited computational resources, acoustic variability, and ethical concerns surrounding bias and privacy. The primary goal is to critically analyze these barriers and identify practical, inclusive strategies to advance ASR technologies within the African context. Recent advances and case studies emphasize promising strategies such as community-driven data collection, self-supervised and multilingual learning, lightweight model architectures, and techniques that prioritize privacy. Evidence from pilot projects involving various African languages showcases the feasibility and impact of customized solutions, which encompass morpheme-based modeling and domain-specific ASR applications in sectors like healthcare and education. The findings highlight the importance of interdisciplinary collaboration and sustained investment to tackle the distinct linguistic and infrastructural challenges faced by the continent. This study offers a progressive roadmap for creating ethical, efficient, and inclusive ASR systems that not only safeguard linguistic diversity but also improve digital accessibility and promote socioeconomic participation for speakers of African languages.
Natural Language Processing is a crucial frontier in artificial intelligence, with broad applications in many areas, including public health, agriculture, education, and commerce. However, due to the lack of substantial linguistic resources, many African languages remain underrepresented in this digital transformation. This paper presents a case study on the development of linguistic corpora for three under-resourced Kenyan languages, Kidaw'ida, Kalenjin, and Dholuo, with the aim of advancing natural language processing and linguistic research in African communities. Our project, which lasted one year, employed a selective crowd-sourcing methodology to collect text and speech data from native speakers of these languages. Data collection involved (1) recording conversations and translation of the resulting text into Kiswahili, thereby creating parallel corpora, and (2) reading and recording written texts to generate speech corpora. We made these resources freely accessible via open-research platforms, namely Zenodo for the parallel text corpora and Mozilla Common Voice for the speech datasets, thus facilitating ongoing contributions and access for developers to train models and develop Natural Language Processing applications. The project demonstrates how grassroots efforts in corpus building can support the inclusion of African languages in artificial intelligence innovations. In addition to filling resource gaps, these corpora are vital in promoting linguistic diversity and empowering local communities by enabling Natural Language Processing applications tailored to their needs. As African countries like Kenya increasingly embrace digital transformation, developing indigenous language resources becomes essential for inclusive growth. We encourage continued collaboration from native speakers and developers to expand and utilize these corpora.
Tadesse Destaw Belay, Israel Abebe Azime, Ibrahim Said Ahmad
et al.
Language models built from various sources are the foundation of today's NLP progress. However, for many low-resource languages, the diversity of domains is often limited, more biased to a religious domain, which impacts their performance when evaluated on distant and rapidly evolving domains such as social media. Domain adaptive pre-training (DAPT) and task-adaptive pre-training (TAPT) are popular techniques to reduce this bias through continual pre-training for BERT-based models, but they have not been explored for African multilingual encoders. In this paper, we explore DAPT and TAPT continual pre-training approaches for African languages social media domain. We introduce AfriSocial, a large-scale social media and news domain corpus for continual pre-training on several African languages. Leveraging AfriSocial, we show that DAPT consistently improves performance (from 1% to 30% F1 score) on three subjective tasks: sentiment analysis, multi-label emotion, and hate speech classification, covering 19 languages. Similarly, leveraging TAPT on the data from one task enhances performance on other related tasks. For example, training with unlabeled sentiment data (source) for a fine-grained emotion classification task (target) improves the baseline results by an F1 score ranging from 0.55% to 15.11%. Combining these two methods (i.e. DAPT + TAPT) further improves the overall performance. The data and model resources are available at HuggingFace.
Chris Emezue, NaijaVoices Community, Busayo Awobade
et al.
The development of high-performing, robust, and reliable speech technologies depends on large, high-quality datasets. However, African languages -- including our focus, Igbo, Hausa, and Yoruba -- remain under-represented due to insufficient data. Popular voice-enabled technologies do not support any of the 2000+ African languages, limiting accessibility for circa one billion people. While previous dataset efforts exist for the target languages, they lack the scale and diversity needed for robust speech models. To bridge this gap, we introduce the NaijaVoices dataset, a 1,800-hour speech-text dataset with 5,000+ speakers. We outline our unique data collection approach, analyze its acoustic diversity, and demonstrate its impact through finetuning experiments on automatic speech recognition, averagely achieving 75.86% (Whisper), 52.06% (MMS), and 42.33% (XLSR) WER improvements. These results highlight NaijaVoices' potential to advance multilingual speech processing for African languages.
Ibrahim Said Ahmad, Shiran Dudy, Tadesse Destaw Belay
et al.
Understanding how emotions are expressed across languages is vital for building culturally-aware and inclusive NLP systems. However, emotion expression in African languages is understudied, limiting the development of effective emotion detection tools in these languages. In this work, we present a cross-linguistic analysis of emotion expression in 15 African languages. We examine four key dimensions of emotion representation: text length, sentiment polarity, emotion co-occurrence, and intensity variations. Our findings reveal diverse language-specific patterns in emotional expression -- with Somali texts typically longer, while others like IsiZulu and Algerian Arabic show more concise emotional expression. We observe a higher prevalence of negative sentiment in several Nigerian languages compared to lower negativity in languages like IsiXhosa. Further, emotion co-occurrence analysis demonstrates strong cross-linguistic associations between specific emotion pairs (anger-disgust, sadness-fear), suggesting universal psychological connections. Intensity distributions show multimodal patterns with significant variations between language families; Bantu languages display similar yet distinct profiles, while Afroasiatic languages and Nigerian Pidgin demonstrate wider intensity ranges. These findings highlight the need for language-specific approaches to emotion detection while identifying opportunities for transfer learning across related languages.
Addressing educational inequity in Sub-Saharan Africa, this research presents an autonomous agent-orchestrated framework for decentralized, culturally adaptive educational content generation on edge devices. The system leverages four specialized agents that work together to generate contextually appropriate educational content. Experimental validation on platforms including Raspberry Pi 4B and NVIDIA Jetson Nano demonstrates significant performance achievements. InkubaLM on Jetson Nano achieved a Time-To-First-Token (TTFT) of 129 ms, an average inter-token latency of 33 ms, and a throughput of 45.2 tokens per second while consuming 8.4 W. On Raspberry Pi 4B, InkubaLM also led with 326 ms TTFT and 15.9 tokens per second at 5.8 W power consumption. The framework consistently delivered high multilingual quality, averaging a BLEU score of 0.688, cultural relevance of 4.4/5, and fluency of 4.2/5 across tested African languages. Through potential partnerships with active community organizations including African Youth & Community Organization (AYCO) and Florida Africa Foundation, this research aims to establish a practical foundation for accessible, localized, and sustainable AI-driven education in resource-constrained environments. Keeping focus on long-term viability and cultural appropriateness, it contributes to United Nations SDGs 4, 9, and 10. Index Terms - Multi-Agent Systems, Edge AI Computing, Educational Technology, African Languages, Rural Education, Sustainable Development, UN SDG.
Considering their important role in human life the study of emotions is of great interest for linguistic science. This article is dedicated to the analysis of the phenomenon of somatization of sadness and the explanation of differences in the levels of such somatization as reflected in language.
The analysis of literature has shown that expression of sadness with the help of somatic expressions is particularly prevalent in African, South-East Asian and Australian languages. Organs that are most often associated with emotions are the heart, liver and stomach and interoception plays a great role in creating an association between an organ and an emotion. With its help a person becomes aware of the physical changes taking place inside their body, which can be caused in particular by emotions. It was established that certain associations between organs and emotions come to exist due to “somatic bridges” while others form because of “semantic shift”. It was found that the frequency of the use of somatic expressions that express emotions was reduced in English during the industrialization and that similar changes are taking place today in Chinese.
In order to explain the differences in the level of somatization it is useful to turn to the triadic structure of concepts, in accordance to which the concept “sadness” has an experiential side (an interoceptive characterization of the emotion), a notional side (a definition, verbal representation etc.) and an evaluative side. It is hypothesized that an important role of somatic expression in the expression of sadness points to the importance of the experiential side while the use of abstract words is indicative of the notional side being important. The fact that the experiential side of a concept is considered to predate the notional side explains the direction of the diachronic change from stronger somatization of emotions towards their expression with the help of more abstract notions.
Jesujoba O. Alabi, Xuechen Liu, Dietrich Klakow
et al.
In this work, we present AfriHuBERT, an extension of mHuBERT-147, a compact self-supervised learning (SSL) model pretrained on 147 languages. While mHuBERT-147 covered 16 African languages, we expand this to 1,226 through continued pretraining on 10K+ hours of speech data from diverse sources, benefiting an African population of over 600M. We evaluate AfriHuBERT on two key speech tasks, Spoken Language Identification (SLID) and Automatic Speech Recognition (ASR), using the FLEURS benchmark. Our results show a +3.6% F1 score improvement for SLID and a -2.1% average Word Error Rate (WER) reduction for ASR over mHuBERT-147, and demonstrates competitiveness with larger SSL models such as MMS and XEUS. Further analysis shows that ASR models trained on AfriHuBERT exhibit improved cross-corpus generalization and are competitive in extremely low-resource ASR scenarios.
Edward Bayes, Israel Abebe Azime, Jesujoba O. Alabi
et al.
Evaluations of Large Language Models (LLMs) on knowledge-intensive tasks and factual accuracy often focus on high-resource languages primarily because datasets for low-resource languages (LRLs) are scarce. In this paper, we present Uhura -- a new benchmark that focuses on two tasks in six typologically-diverse African languages, created via human translation of existing English benchmarks. The first dataset, Uhura-ARC-Easy, is composed of multiple-choice science questions. The second, Uhura-TruthfulQA, is a safety benchmark testing the truthfulness of models on topics including health, law, finance, and politics. We highlight the challenges creating benchmarks with highly technical content for LRLs and outline mitigation strategies. Our evaluation reveals a significant performance gap between proprietary models such as GPT-4o and o1-preview, and Claude models, and open-source models like Meta's LLaMA and Google's Gemma. Additionally, all models perform better in English than in African languages. These results indicate that LMs struggle with answering scientific questions and are more prone to generating false claims in low-resource African languages. Our findings underscore the necessity for continuous improvement of multilingual LM capabilities in LRL settings to ensure safe and reliable use in real-world contexts. We open-source the Uhura Benchmark and Uhura Platform to foster further research and development in NLP for LRLs.
Colin Leong, Herumb Shandilya, Bonaventure F. P. Dossou
et al.
Many natural language processing (NLP) tasks make use of massively pre-trained language models, which are computationally expensive. However, access to high computational resources added to the issue of data scarcity of African languages constitutes a real barrier to research experiments on these languages. In this work, we explore the applicability of low-compute approaches such as language adapters in the context of this low-resource double-bind. We intend to answer the following question: do language adapters allow those who are doubly bound by data and compute to practically build useful models? Through fine-tuning experiments on African languages, we evaluate their effectiveness as cost-effective approaches to low-resource African NLP. Using solely free compute resources, our results show that language adapters achieve comparable performances to massive pre-trained language models which are heavy on computational resources. This opens the door to further experimentation and exploration on full-extent of language adapters capacities.
From Word2Vec to GloVe, word embedding models have played key roles in the current state-of-the-art results achieved in Natural Language Processing. Designed to give significant and unique vectorized representations of words and entities, those models have proven to efficiently extract similarities and establish relationships reflecting semantic and contextual meaning among words and entities. African Languages, representing more than 31% of the worldwide spoken languages, have recently been subject to lots of research. However, to the best of our knowledge, there are currently very few to none word embedding models for those languages words and entities, and none for the languages under study in this paper. After describing Glove, Word2Vec, and Poincaré embeddings functionalities, we build Word2Vec and Poincaré word embedding models for Fon and Nobiin, which show promising results. We test the applicability of transfer learning between these models as a landmark for African Languages to jointly involve in mitigating the scarcity of their resources, and attempt to provide linguistic and social interpretations of our results. Our main contribution is to arouse more interest in creating word embedding models proper to African Languages, ready for use, and that can significantly improve the performances of Natural Language Processing downstream tasks on them. The official repository and implementation is at https://github.com/bonaventuredossou/afrivec
This work supports further development of language technology for the languages of Africa by providing a Wikidata-derived resource of name lists corresponding to common entity types (person, location, and organization). While we are not the first to mine Wikidata for name lists, our approach emphasizes scalability and replicability and addresses data quality issues for languages that do not use Latin scripts. We produce lists containing approximately 1.9 million names across 28 African languages. We describe the data, the process used to produce it, and its limitations, and provide the software and data for public use. Finally, we discuss the ethical considerations of producing this resource and others of its kind.
This paper contributes to the typological debate of whether sign languages should be divided into manual versus non-manual dominant languages, w.r.t. negation, a distinction that has recently been challenged (Johnston 2018) or argued to be too radical (Oomen & Pfau 2017), by providing a characterization of negation in South African Sign Language (SASL). It has also been observed in several sign languages that a construction which consists of a yes-no question followed by a negative fragment answer, both produced by the same speaker, can be used to negate a proposition. While this question-answer pair construction has received attention in the recent sign language literature, it is only mentioned in passing in the literature on negation. In this paper, I provide an analysis of these polar question-answer clauses as a grammaticalized negation strategy in SASL, following Caponigro and Davidson’s (2011) analysis of this construction in ASL.
The contrast between the need for large amounts of data for current Natural Language Processing (NLP) techniques, and the lack thereof, is accentuated in the case of African languages, most of which are considered low-resource. To help circumvent this issue, we explore techniques exploiting the qualities of morphologically rich languages (MRLs), while leveraging pretrained word vectors in well-resourced languages. In our exploration, we show that a meta-embedding approach combining both pretrained and morphologically-informed word embeddings performs best in the downstream task of Xhosa-English translation.