Modelling Interaction of Sentence Pair with coupled-LSTMs
This addresses a limitation in natural language processing where existing methods encode sentences separately with minimal cross-sentence information, offering an incremental improvement for tasks requiring sentence pair modeling.
The paper tackles the problem of modeling interactions between sentence pairs by proposing a deep architecture with two coupled-LSTMs that capture interdependencies, achieving state-of-the-art results on two large datasets.
Recently, there is rising interest in modelling the interactions of two sentences with deep neural networks. However, most of the existing methods encode two sequences with separate encoders, in which a sentence is encoded with little or no information from the other sentence. In this paper, we propose a deep architecture to model the strong interaction of sentence pair with two coupled-LSTMs. Specifically, we introduce two coupled ways to model the interdependences of two LSTMs, coupling the local contextualized interactions of two sentences. We then aggregate these interactions and use a dynamic pooling to select the most informative features. Experiments on two very large datasets demonstrate the efficacy of our proposed architecture and its superiority to state-of-the-art methods.