Modelling Sentence Pairs with Tree-structured Attentive Encoder

10/10/2016
by   Yao Zhou, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/03/2021

Attentive Tree-structured Network for Monotonicity Reasoning

Many state-of-art neural models designed for monotonicity reasoning perf...
research
11/06/2018

Learning to Embed Sentences Using Attentive Recursive Trees

Sentence embedding is an effective feature representation for most deep ...
research
05/29/2018

Semantic Sentence Matching with Densely-connected Recurrent and Co-attentive Information

Sentence matching is widely used in various natural language tasks such ...
research
04/30/2017

Tree-Structured Neural Machine for Linguistics-Aware Sentence Generation

Different from other sequential data, sentences in natural language are ...
research
04/29/2020

"The Boating Store Had Its Best Sail Ever": Pronunciation-attentive Contextualized Pun Recognition

Humor plays an important role in human languages and it is essential to ...
research
09/20/2023

Attentive VQ-VAE

We present a novel approach to enhance the capabilities of VQVAE models ...
research
01/13/2022

Recognizing semantic relation in sentence pairs using Tree-RNNs and Typed dependencies

Recursive neural networks (Tree-RNNs) based on dependency trees are ubiq...

Please sign up or login with your details

Forgot password? Click here to reset