Task-Oriented Dialog Systems for the Senegalese Wolof Language

TL;DR

This paper presents a modular task-oriented dialogue system for the low-resource Wolof language, leveraging Rasa and a machine translation system to improve chatbot control and extendability to other low-resource languages.

Contribution

It introduces a novel, modular approach using Rasa and machine translation for Wolof, demonstrating effective intent classification comparable to resource-rich languages.

Findings

Wolof intent classifier performs similarly to French.

The approach is extensible to other low-resource languages.

The system offers better control over outputs compared to LLMs.

Abstract

In recent years, we are seeing considerable interest in conversational agents with the rise of large language models (LLMs). Although they offer considerable advantages, LLMs also present significant risks, such as hallucination, which hinder their widespread deployment in industry. Moreover, low-resource languages such as African ones are still underrepresented in these systems limiting their performance in these languages. In this paper, we illustrate a more classical approach based on modular architectures of Task-oriented Dialog Systems (ToDS) offering better control over outputs. We propose a chatbot generation engine based on the Rasa framework and a robust methodology for projecting annotations onto the Wolof language using an in-house machine translation system. After evaluating a generated chatbot trained on the Amazon Massive dataset, our Wolof Intent Classifier performs similarly to the one obtained for French, which is a resource-rich language. We also show that this approach is extensible to other low-resource languages, thanks to the intent classifier's language-agnostic pipeline, simplifying the design of chatbots in these languages.