Syntax-based Deep Matching of Short Texts

By Mingxuan Wang, Zhengdong Lu, Hang Li, Qun Liu. 2015

87 citations recorded by the source corpus.

Many tasks in natural language processing, ranging from machine translation to question answering, can be reduced to the problem of matching two sentences or more generally two short texts. We propose a new approach to the problem, called Deep Match Tree (DeepMatch$_{tree}$), under a general setting. The approach consists of two components, 1) a mining algorithm to discover patterns for matching two short-texts, defined in the product space of dependency trees, and 2) a deep neural network for matching short texts using the mined patterns, as well as a learning algorithm to build the network having a sparse structure. We test our algorithm on the problem of matching a tweet and a response in social media, a hard matching problem proposed in [Wang et al., 2013], and show that DeepMatch$_{tree}$ can outperform a number of competitor models including one without using dependency trees and one based on word-embedding, all with large margins

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

A Deep Relevance Matching Model for Ad-hoc Retrieval (2016, background): “[28] proposed Deep Match Tree (DeepMatchtree) for the short text matching problem.”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, methodology): “architecture to learn the representation of message and response, or directly learn the interacted representation of two sentences, followed by a multi-layer perceptron to compute the matching score. [92] extracted dependency tree matching patterns and used them as sparse one-hot inputs of a deep fe”
Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network (2018, background): “Most early studies are single-turn that only consider the last utterance for matching response (Wang et al., 2013, 2015).”