For text matching problems in natural language processing, this paper proposed a deep learning model based on self-adaptive affinity graph learning framework for short text matching. The affinity graph can be converted into a vector form using word embedding, and then obtained by constructing a text similarity relationship matrix, which can express the neighbor relationship of the text sample. Current methods usually construct static affinity graphs, which rely on prior knowledge and hard to obtain the optimal representation of sentence pairs. Therefore, this paper proposed using the Siamese CNN to learn the affinity graph of better dynamic updates. The accuracy and F₁ values of the model on the Quora dataset are 84.15% and 79.88%, and on the MSRP dataset are 74.55% and 81.63%. Experiments show that the proposed model can improve the accuracy of text recognition and matching effectively.

[2020-06-05] Printed Article /doc/2018.12.0877/v2