Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Modelling Sentence Pairs with Tree-structured Attentive Encoder

About

We describe an attentive encoder that combines tree-structured recursive neural networks and sequential recurrent neural networks for modelling sentence pairs. Since existing attentive models exert attention on the sequential structure, we propose a way to incorporate attention into the tree topology. Specially, given a pair of sentences, our attentive encoder uses the representation of one sentence, which generated via an RNN, to guide the structural encoding of the other sentence on the dependency parse tree. We evaluate the proposed attentive encoder on three tasks: semantic similarity, paraphrase identification and true-false question selection. Experimental results show that our encoder outperforms all baselines and achieves state-of-the-art results on two tasks.

Yao Zhou, Cong Liu, Yan Pan• 2016

Related benchmarks

TaskDatasetResultRank
Semantic RelatednessSICK (test)
MSE0.243
4
Showing 1 of 1 rows

Other info

Follow for update