Text Categorization Can Enhance Domain-Agnostic Stopword Extraction
This research enhances NLP for African languages by providing a hybrid method for stopword extraction, though it is incremental as it combines existing statistical and linguistic approaches.
The paper tackled the problem of identifying domain-agnostic stopwords for NLP in African languages and French, finding that text categorization achieved over 80% detection success for most languages but varied due to linguistic differences.
This paper investigates the role of text categorization in streamlining stopword extraction in natural language processing (NLP), specifically focusing on nine African languages alongside French. By leveraging the MasakhaNEWS, African Stopwords Project, and MasakhaPOS datasets, our findings emphasize that text categorization effectively identifies domain-agnostic stopwords with over 80% detection success rate for most examined languages. Nevertheless, linguistic variances result in lower detection rates for certain languages. Interestingly, we find that while over 40% of stopwords are common across news categories, less than 15% are unique to a single category. Uncommon stopwords add depth to text but their classification as stopwords depends on context. Therefore combining statistical and linguistic approaches creates comprehensive stopword lists, highlighting the value of our hybrid method. This research enhances NLP for African languages and underscores the importance of text categorization in stopword extraction.