Improved Text Language Identification for the South African Languages
This work addresses a domain-specific problem for multilingual natural language processing pipelines in South Africa, with incremental improvements to existing methods.
The paper tackles the problem of text language identification for South African languages in short messages, achieving a 31% reduction in language detection error by combining a naive Bayes classifier for language family prediction with a lexicon-based classifier for specific language identification.
Virtual assistants and text chatbots have recently been gaining popularity. Given the short message nature of text-based chat interactions, the language identification systems of these bots might only have 15 or 20 characters to make a prediction. However, accurate text language identification is important, especially in the early stages of many multilingual natural language processing pipelines. This paper investigates the use of a naive Bayes classifier, to accurately predict the language family that a piece of text belongs to, combined with a lexicon based classifier to distinguish the specific South African language that the text is written in. This approach leads to a 31% reduction in the language detection error. In the spirit of reproducible research the training and testing datasets as well as the code are published on github. Hopefully it will be useful to create a text language identification shared task for South African languages.