None Class Ranking Loss for Document-Level Relation Extraction

05/01/2022
by   Yang Zhou, et al.
0

Document-level relation extraction (RE) aims at extracting relations among entities expressed across multiple sentences, which can be viewed as a multi-label classification problem. In a typical document, most entity pairs do not express any pre-defined relation and are labeled as "none" or "no relation". For good document-level RE performance, it is crucial to distinguish such none class instances (entity pairs) from those of pre-defined classes (relations). However, most existing methods only estimate the probability of pre-defined relations independently without considering the probability of "no relation". This ignores the context of entity pairs and the label correlations between the none class and pre-defined classes, leading to sub-optimal predictions. To address this problem, we propose a new multi-label loss that encourages large margins of label confidence scores between each pre-defined class and the none class, which enables captured label correlations and context-dependent thresholding for label prediction. To gain further robustness against positive-negative imbalance and mislabeled data that could appear in real-world RE datasets, we propose a margin regularization and a margin shifting technique. Experimental results demonstrate that our method significantly outperforms existing multi-label losses for document-level RE and works well in other multi-label tasks such as emotion classification when none class instances are available for training.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/21/2020

Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling

Document-level relation extraction (RE) poses new challenges compared to...
research
12/20/2022

Document-level Relation Extraction with Relation Correlations

Document-level relation extraction faces two overlooked challenges: long...
research
04/03/2023

Towards Integration of Discriminability and Robustness for Document-Level Relation Extraction

Document-level relation extraction (DocRE) predicts relations for entity...
research
05/14/2019

Assessing the Difficulty of Classifying ConceptNet Relations in a Multi-Label Classification Setting

Commonsense knowledge relations are crucial for advanced NLU tasks. We e...
research
06/21/2019

Exploiting Entity BIO Tag Embeddings and Multi-task Learning for Relation Extraction with Imbalanced Data

In practical scenario, relation extraction needs to first identify entit...
research
04/27/2022

Document-Level Relation Extraction with Sentences Importance Estimation and Focusing

Document-level relation extraction (DocRE) aims to determine the relatio...
research
04/10/2023

Asymmetric Polynomial Loss For Multi-Label Classification

Various tasks are reformulated as multi-label classification problems, i...

Please sign up or login with your details

Forgot password? Click here to reset