Relation Extraction with Explanation

05/28/2020
by   Hamed Shahbazi, et al.
0

Recent neural models for relation extraction with distant supervision alleviate the impact of irrelevant sentences in a bag by learning importance weights for the sentences. Efforts thus far have focused on improving extraction accuracy but little is known about their explainability. In this work we annotate a test set with ground-truth sentence-level explanations to evaluate the quality of explanations afforded by the relation extraction models. We demonstrate that replacing the entity mentions in the sentences with their fine-grained entity types not only enhances extraction accuracy but also improves explanation. We also propose to automatically generate "distractor" sentences to augment the bags and train the model to ignore the distractors. Evaluations on the widely used FB-NYT dataset show that our methods achieve new state-of-the-art accuracy while improving model explainability.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/10/2021

D-REX: Dialogue Relation Extraction with Explanations

Existing research studies on cross-sentence relation extraction in long-...
research
12/08/2020

From Bag of Sentences to Document: Distantly Supervised Relation Extraction via Machine Reading Comprehension

Distant supervision (DS) is a promising approach for relation extraction...
research
04/25/2022

It Takes Two Flints to Make a Fire: Multitask Learning of Neural Relation and Explanation Classifiers

We propose an explainable approach for relation extraction that mitigate...
research
10/17/2020

Active Testing: An Unbiased Evaluation Method for Distantly Supervised Relation Extraction

Distant supervision has been a widely used method for neural relation ex...
research
04/16/2021

Re-TACRED: Addressing Shortcomings of the TACRED Dataset

TACRED is one of the largest and most widely used sentence-level relatio...
research
05/08/2022

GRAPHCACHE: Message Passing as Caching for Sentence-Level Relation Extraction

Entity types and textual context are essential properties for sentence-l...
research
04/19/2019

Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction

In recent years there is surge of interest in applying distant supervisi...

Please sign up or login with your details

Forgot password? Click here to reset