New Bangla Sentence Function Classification Corpus Developed

Researchers have developed a new corpus of 10,000 Bangla sentences, manually categorized into declarative, interrogative, imperative, and exclamatory functions, to address the limited resources for Bangla sentence function classification. The study evaluated various feature representations, including Bag-of-Words, TF-IDF, and Word2Vec, alongside classical machine learning classifiers and ensemble models. The Double-Level Ensemble model combined with TF-IDF features achieved the highest performance, with an accuracy and macro-F1 score of 0.95, demonstrating the effectiveness of sparse lexical representations and ensemble learning for this NLP task. AI

IMPACT Establishes a new benchmark and baseline models for Bangla sentence function classification, potentially improving downstream NLP applications for the language.

RANK_REASON The item is an academic paper detailing corpus development and model benchmarking for a specific NLP task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• bag-of-words model
• Bangla
• Double-Level Ensemble
• Single-Level Ensemble
• tf–idf
• Word2vec

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →