What is relation extraction? Application, Description

Relation extraction plays an important role in extracting structured information from unstructured sources such as raw text. For example, interactions between drugs, understanding scene, relationships among people.
http://deepdive.stanford.edu/relation_extraction

TAC KBP SF - Text Analysis Conference Knowledge Base Population Slot Filling

by US National Institute of Standards and Technology

goal of KBP : populating knowledge bases from unstructured text.
slot filling : to search the document collection to fill in values for specific attributes("slots") for specific entities.

Recent Relation Extraction Papers

ACL 2018

A Walk-based Model on Entity Graphs for Relation Extraction
ACE 2005

DSGAN: Generative Adversarial Training for Distant Supervision Relation Extraction

Robust Distant Supervision Relation Extraction via Deep Reinforcement Learning


EMNLP 2018

Extracting Entities and Relations with Joint Minimum Risk Training
ACE 2005

Multi-Level Structured Self-Attentions for Distantly Supervised Relation Extraction
distant supervision

Hierarchical Relation Extraction with Coarse-to-Fine Grained Attention

Large-scale Exploration of Neural Relation Classification Architectures

Neural Relation Extraction via Inner-Sentence Noise Reduction and Transfer Learning

Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction

RESIDE: Improving Distantly-Supervised Neural Relation Extraction using Side Information

Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
SEMEVAL 2010, TACRED


EMNLP 2017

Adversarial Training for Relation Extraction
NYT

A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction
Distant supervision, Freebase, P@N

Position-aware Attention and Supervised Data Improve Slot Filling
TACRED


==================================================
Position-aware Self-attention with Relative Positional Encodings for Slot Filling