Document-Level Relation Extraction with Sentences Importance Estimation and Focusing

04/27/2022
by   Wang Xu, et al.
0

Document-level relation extraction (DocRE) aims to determine the relation between two entities from a document of multiple sentences. Recent studies typically represent the entire document by sequence- or graph-based models to predict the relations of all entity pairs. However, we find that such a model is not robust and exhibits bizarre behaviors: it predicts correctly when an entire test document is fed as input, but errs when non-evidence sentences are removed. To this end, we propose a Sentence Importance Estimation and Focusing (SIEF) framework for DocRE, where we design a sentence importance score and a sentence focusing loss, encouraging DocRE models to focus on evidence sentences. Experimental results on two domains show that our SIEF not only improves overall performance, but also makes DocRE models more robust. Moreover, SIEF is a general framework, shown to be effective when combined with a variety of base DocRE models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2023

Document-level Relation Extraction with Cross-sentence Reasoning Graph

Relation extraction (RE) has recently moved from the sentence-level to d...
research
06/03/2021

Three Sentences Are All You Need: Local Path Enhanced Document Relation Extraction

Document-level Relation Extraction (RE) is a more challenging task than ...
research
04/01/2022

NC-DRE: Leveraging Non-entity Clue Information for Document-level Relation Extraction

Document-level relation extraction (RE), which requires reasoning on mul...
research
02/17/2023

DREEAM: Guiding Attention with Evidence for Improving Document-Level Relation Extraction

Document-level relation extraction (DocRE) is the task of identifying al...
research
10/14/2021

Making Document-Level Information Extraction Right for the Right Reasons

Document-level information extraction is a flexible framework compatible...
research
05/13/2020

Reasoning with Latent Structure Refinement for Document-Level Relation Extraction

Document-level relation extraction requires integrating information with...
research
05/01/2022

None Class Ranking Loss for Document-Level Relation Extraction

Document-level relation extraction (RE) aims at extracting relations amo...

Please sign up or login with your details

Forgot password? Click here to reset