Vector-quantization-based topic modeling

Abstract

With the purpose of learning and utilizing explicit and dense topic embeddings, we propose three variations of novel vector-quantization-based topic models (VQ-TMs): (1) Hard VQ-TM, (2) Soft VQ-TM, and (3) Multi-View Soft VQ-TM. The model family capitalize on vector quantization techniques, embedded input documents, and viewing words as mixtures of topics. Guided by a comprehensive set of evaluation metrics, we conduct systematic quantitative and qualitative empirical studies, and demonstrate the superior performance of VQ-TMs compared to important baseline models. Through a unique case study on code generation from natural language descriptions, we further illustrate the power of VQ-TMs in downstream tasks.