Long Text QA Matching Model Based on BiGRU–DAttention–DSSM

QA matching is a very important task in natural language processing, but current research on text focuses more short rather than long matching. Compared with matching, rich information, distracting information frequent. This paper extracted question-and-answer pairs about psychological counseling to QA-matching technology based deep learning. We adjusted DSSM (Deep Structured Semantic Model) make it suitable for the task. Moreover, better extraction of features, we also improved by enriching representation layer, using bidirectional neural network and attention mechanism. The experimental results show that BiGRU–Dattention–DSSM performs at questions answers.