# Advancing Conversational AI with Shona Slang: A Dataset and Hybrid Model for Digital Inclusion

arXiv: https://arxiv.org/abs/2509.14249 · HTML: https://mlsanity.com/paper/2509.14249/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 10 Sep 2025.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [The State and Fate of Linguistic Diversity and Inclusion in the NLP World](https://mlsanity.com/paper/2004.09095/) (2020)
- [An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction](https://mlsanity.com/paper/1909.02027/) (2019)
- [BERTweet: A pre-trained language model for English Tweets](https://mlsanity.com/paper/2005.10200/) (2020)
- [Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages](https://mlsanity.com/paper/2010.02353/) (2020)

## Abstract (arXiv)

African languages remain underrepresented in natural language processing (NLP), with most corpora limited to formal registers that fail to capture the vibrancy of everyday communication. This work addresses this gap for Shona, a Bantu language spoken in Zimbabwe and Zambia, by introducing a novel Shona--English slang dataset curated from anonymized social media conversations. The dataset is annotated for intent, sentiment, dialogue acts, code-mixing, and tone, and is publicly available at https://github.com/HappymoreMasoka/Workingwithshona-slang. We fine-tuned a multilingual DistilBERT classifier for intent recognition, achieving 96.4% accuracy and 96.3% F1-score, hosted at https://huggingface.co/HappymoreMasoka. This classifier is integrated into a hybrid chatbot that combines rule-based responses with retrieval-augmented generation (RAG) to handle domain-specific queries, demonstrated through a use case assisting prospective students with graduate program information at Pace University. Qualitative evaluation shows the hybrid system outperforms a RAG-only baseline in cultural relevance and user engagement. By releasing the dataset, model, and methodology, this work advances NLP resources for African languages, promoting inclusive and culturally resonant conversational AI.