SRE-Net Model for Automatic Social Relation Extraction from Video

2018 ◽  
pp. 442-460
Author(s):  
Lili Zhou ◽  
Bin Wu ◽  
Jinna Lv
Keyword(s):  
Social Relation ◽  
Relation Extraction

Social Relation Extraction Based on Chinese Wikipedia Articles

2013 ◽  
pp. 94-101 ◽  
Author(s):  
Maofu Liu ◽  
Yu Xiao ◽  
Chunwei Lei ◽  
Xin Zhou
Keyword(s):  
Social Relation ◽  
Relation Extraction

scholarly journals TransNet: Translation-Based Network Representation Learning for Social Relation Extraction

2017 ◽  
Author(s):  
Cunchao Tu ◽  
Zhengyan Zhang ◽  
Zhiyuan Liu ◽  
Maosong Sun
Keyword(s):  
Semantic Information ◽  
Social Relation ◽  
Source Code ◽  
Relation Extraction ◽  
Representation Learning ◽  
Experimental Results ◽  
Network Representation ◽  
Low Dimensional

Conventional network representation learning (NRL) models learn low-dimensional vertex representations by simply regarding each edge as a binary or continuous value. However, there exists rich semantic information on edges and the interactions between vertices usually preserve distinct meanings, which are largely neglected by most existing NRL models. In this work, we present a novel Translation-based NRL model, TransNet, by regarding the interactions between vertices as a translation operation. Moreover, we formalize the task of Social Relation Extraction (SRE) to evaluate the capability of NRL methods on modeling the relations between vertices. Experimental results on SRE demonstrate that TransNet significantly outperforms other baseline methods by 10% to 20% on hits@1. The source code and datasets can be obtained from https://github.com/thunlp/TransNet.

Sign in / Sign up

Export Citation Format

Share Document