Word-level dual channel with multi-head semantic attention interaction for community question answering

Word-level dual channel with multi-head semantic attention interaction for community question answering

Blog Article

The semantic matching problem detects whether the candidate text is related to a specific input text.Basic text matching adopts the method of statistical vocabulary information without considering semantic relevance.Methods based on Convolutional neural networks (CNN) and Cleaning / Dishwashing Aprons Recurrent networks (RNN) provide a more optimized structure that can merge the information in the entire sentence into a single sentence-level representation.However, these representations are often not suitable for sentence interactive learning.

We design a multi-dimensional semantic interactive learning model based on the mechanism of multiple written heads in the tapered-breast-plate transformer architecture, which not only considers the correlation and position information between different word levels but also further maps the representation of the sentence to the interactive three-dimensional space, so as to solve the problem and the answer can select the best word-level matching pair, respectively.Experimentally, the algorithm in this paper was tested on Yahoo! and StackEx open-domain datasets.The results show that the performance of the method proposed in this paper is superior to the previous CNN/RNN and BERT-based methods.