Attentive Recurrent Tensor Model for Community Question Answering
This addresses the problem of improving answer quality in community question answering platforms, representing an incremental advance with specific performance gains.
The paper tackled the lexical and semantic gap in community question answering by proposing an attentive recurrent tensor network with token-level and phrase-level attention and 3-way tensor interactions, achieving state-of-the-art performance on answer sentence selection (TrecQA and WikiQA datasets) and outperforming current methods on best answer selection (Yahoo! L4) and answer triggering (WikiQA).
A major challenge to the problem of community question answering is the lexical and semantic gap between the sentence representations. Some solutions to minimize this gap includes the introduction of extra parameters to deep models or augmenting the external handcrafted features. In this paper, we propose a novel attentive recurrent tensor network for solving the lexical and semantic gap in community question answering. We introduce token-level and phrase-level attention strategy that maps input sequences to the output using trainable parameters. Further, we use the tensor parameters to introduce a 3-way interaction between question, answer and external features in vector space. We introduce simplified tensor matrices with L2 regularization that results in smooth optimization during training. The proposed model achieves state-of-the-art performance on the task of answer sentence selection (TrecQA and WikiQA datasets) while outperforming the current state-of-the-art on the tasks of best answer selection (Yahoo! L4) and answer triggering task (WikiQA).