Match-SRNN: Modeling the Recursive Matching Structure with Spatial RNN

04/15/2016
by   Shengxian Wan, et al.
0

Semantic matching, which aims to determine the matching degree between two texts, is a fundamental problem for many NLP applications. Recently, deep learning approach has been applied to this problem and significant improvements have been achieved. In this paper, we propose to view the generation of the global interaction between two texts as a recursive process: i.e. the interaction of two texts at each position is a composition of the interactions between their prefixes as well as the word level interaction at the current position. Based on this idea, we propose a novel deep architecture, namely Match-SRNN, to model the recursive matching structure. Firstly, a tensor is constructed to capture the word level interactions. Then a spatial RNN is applied to integrate the local interactions recursively, with importance determined by four types of gates. Finally, the matching score is calculated based on the global interaction. We show that, after degenerated to the exact matching scenario, Match-SRNN can approximate the dynamic programming process of longest common subsequence. Thus, there exists a clear interpretation for Match-SRNN. Our experiments on two semantic matching tasks showed the effectiveness of Match-SRNN, and its ability of visualizing the learned matching structure.

READ FULL TEXT
research
01/26/2017

Match-Tensor: a Deep Relevance Model for Search

The application of Deep Neural Networks for ranking in search engines ma...
research
03/09/2015

Syntax-based Deep Matching of Short Texts

Many tasks in natural language processing, ranging from machine translat...
research
10/15/2020

Wasserstein Distance Regularized Sequence Representation for Text Matching in Asymmetrical Domains

One approach to matching texts from asymmetrical domains is projecting t...
research
07/25/2023

Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection

Human-Object Interaction (HOI) detection is a challenging computer visio...
research
01/16/2021

Match-Ignition: Plugging PageRank into Transformer for Long-form Text Matching

Semantic text matching models have been widely used in community questio...
research
10/22/2020

GAN based Unsupervised Segmentation: Should We Match the Exact Number of Objects

The unsupervised segmentation is an increasingly popular topic in biomed...
research
09/15/2021

PoWareMatch: a Quality-aware Deep Learning Approach to Improve Human Schema Matching

Schema matching is a core task of any data integration process. Being in...

Please sign up or login with your details

Forgot password? Click here to reset