CANDiS: Coupled & Attention-Driven Neural Distant Supervision

10/26/2017
by   Tushar Nagarajan, et al.
0

Distant Supervision for Relation Extraction uses heuristically aligned text data with an existing knowledge base as training data. The unsupervised nature of this technique allows it to scale to web-scale relation extraction tasks, at the expense of noise in the training data. Previous work has explored relationships among instances of the same entity-pair to reduce this noise, but relationships among instances across entity-pairs have not been fully exploited. We explore the use of inter-instance couplings based on verb-phrase and entity type similarities. We propose a novel technique, CANDiS, which casts distant supervision using inter-instance coupling into an end-to-end neural network model. CANDiS incorporates an attention module at the instance-level to model the multi-instance nature of this problem. CANDiS outperforms existing state-of-the-art techniques on a standard benchmark dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2018

Denoising Distant Supervision for Relation Extraction via Instance-Level Adversarial Training

Existing neural relation extraction (NRE) models rely on distant supervi...
research
12/22/2016

Noise Mitigation for Neural Entity Typing and Relation Extraction

In this paper, we address two different types of noise in information ex...
research
07/25/2019

Deep Ranking Based Cost-sensitive Multi-label Learning for Distant Supervision Relation Extraction

Knowledge base provides a potential way to improve the intelligence of i...
research
11/19/2015

Knowledge Base Population using Semantic Label Propagation

A crucial aspect of a knowledge base population system that extracts new...
research
12/17/2020

InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction

Distant supervision makes it possible to automatically label bags of sen...
research
10/30/2017

Indirect Supervision for Relation Extraction using Question-Answer Pairs

Automatic relation extraction (RE) for types of interest is of great imp...
research
12/27/2018

Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction

Distant supervision leverages knowledge bases to automatically label ins...

Please sign up or login with your details

Forgot password? Click here to reset