A Novel Framework using Zero Shot Learning Technique for Non-Factoid Question Answering System

Non-Factoid Question Answering (QA) is the next generation of textual QA systems, which gives passage level summaries for a natural language query, posted by user. The main issue lies in appropriateness generated summary. This paper proposes framework non-factoid system, has three components: (i) A deep neural network classifier, produces sentence vector considering word correlation and context. (ii) Zero shot classifier that uses multi-channel Convolutional Neural Network (CNN), to extract knowledge from multiple sources accumulator. output acts as enhancer strengthens (iii) Summary generator Maximal Marginal Relevance (MMR) algorithm, computes similarity among query related answer sentences zero classifier. model applied on datasets WikiPassageQA ANTIQUE. experimental analysis shows this comparatively better results dataset.