Computer Science > Computation and Language
[Submitted on 9 Mar 2015 (v1), last revised 12 Jun 2015 (this version, v6)]
Title:Syntax-based Deep Matching of Short Texts
View PDFAbstract: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
Submission history
From: Mingxuan Wang [view email][v1] Mon, 9 Mar 2015 11:11:15 UTC (1,752 KB)
[v2] Tue, 10 Mar 2015 03:24:58 UTC (1,752 KB)
[v3] Thu, 12 Mar 2015 08:31:01 UTC (1,753 KB)
[v4] Fri, 24 Apr 2015 04:48:25 UTC (1,753 KB)
[v5] Mon, 18 May 2015 13:26:28 UTC (472 KB)
[v6] Fri, 12 Jun 2015 08:26:01 UTC (473 KB)
Current browse context:
cs.CL
References & Citations
Bibliographic and Citation Tools
Bibliographic Explorer (What is the Explorer?)
Litmaps (What is Litmaps?)
scite Smart Citations (What are Smart Citations?)
Code, Data and Media Associated with this Article
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub (What is DagsHub?)
Gotit.pub (What is GotitPub?)
Papers with Code (What is Papers with Code?)
ScienceCast (What is ScienceCast?)
Demos
Recommenders and Search Tools
Influence Flower (What are Influence Flowers?)
Connected Papers (What is Connected Papers?)
CORE Recommender (What is CORE?)
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.