Double attention recurrent convolution neural network for answer selection.

ABSTRACT: Answer selection is one of the key steps in many question answering (QA) applications. In this paper, a new deep model with two kinds of attention is proposed for answer selection: the double attention recurrent convolution neural network (DARCNN). Double attention means self-attention and cross-attention. The design inspiration of this model came from the transformer in the domain of machine translation. Self-attention can directly calculate dependencies between words regardless of the distance. However, self-attention ignores the distinction between its surrounding words and other words. Thus, we design a decay self-attention that prioritizes local words in a sentence. In addition, cross-attention is established to achieve interaction between question and candidate answer. With the outpu

SUBMITTER: Bao G 

PROVIDER: S-EPMC7277251 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature