Harnessing Transfer Learning from Swahili: Advancing Solutions for Comorian Dialects

TL;DR

This paper explores transfer learning from Swahili to develop NLP tools for Comorian dialects, demonstrating promising results in speech recognition and translation despite limited data.

Contribution

It pioneers transfer learning techniques for Comorian languages by leveraging lexical similarities with Swahili, a low-resource language adaptation.

Findings

Achieved ROUGE scores of 0.6826, 0.42, and 0.6532 in MT

Recorded a WER of 39.50% and CER of 13.76% in ASR

Demonstrated feasibility of transfer learning for underrepresented African languages

Abstract

If today some African languages like Swahili have enough resources to develop high-performing Natural Language Processing (NLP) systems, many other languages spoken on the continent are still lacking such support. For these languages, still in their infancy, several possibilities exist to address this critical lack of data. Among them is Transfer Learning, which allows low-resource languages to benefit from the good representation of other languages that are similar to them. In this work, we adopt a similar approach, aiming to pioneer NLP technologies for Comorian, a group of four languages or dialects belonging to the Bantu family. Our approach is initially motivated by the hypothesis that if a human can understand a different language from their native language with little or no effort, it would be entirely possible to model this process on a machine. To achieve this, we consider ways to construct Comorian datasets mixed with Swahili. One thing to note here is that in terms of Swahili data, we only focus on elements that are closest to Comorian by calculating lexical distances between candidate and source data. We empirically test this hypothesis in two use cases: Automatic Speech Recognition (ASR) and Machine Translation (MT). Our MT model achieved ROUGE-1, ROUGE-2, and ROUGE-L scores of 0.6826, 0.42, and 0.6532, respectively, while our ASR system recorded a WER of 39.50\% and a CER of 13.76\%. This research is crucial for advancing NLP in underrepresented languages, with potential to preserve and promote Comorian linguistic heritage in the digital age.