A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Ye, Pan, Huazheng, Zhang, Tao, Wu, Wen, Hu, Wenxin
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916105017098240
author Wang, Ye
Pan, Huazheng
Zhang, Tao
Wu, Wen
Hu, Wenxin
author_facet Wang, Ye
Pan, Huazheng
Zhang, Tao
Wu, Wen
Hu, Wenxin
contents The goal of document-level relation extraction (RE) is to identify relations between entities that span multiple sentences. Recently, incomplete labeling in document-level RE has received increasing attention, and some studies have used methods such as positive-unlabeled learning to tackle this issue, but there is still a lot of room for improvement. Motivated by this, we propose a positive-augmentation and positive-mixup positive-unlabeled metric learning framework (P3M). Specifically, we formulate document-level RE as a metric learning problem. We aim to pull the distance closer between entity pair embedding and their corresponding relation embedding, while pushing it farther away from the none-class relation embedding. Additionally, we adapt the positive-unlabeled learning to this loss objective. In order to improve the generalizability of the model, we use dropout to augment positive samples and propose a positive-none-class mixup method. Extensive experiments show that P3M improves the F1 score by approximately 4-10 points in document-level RE with incomplete labeling, and achieves state-of-the-art results in fully labeled scenarios. Furthermore, P3M has also demonstrated robustness to prior estimation bias in incomplete labeled scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2306_14806
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling
Wang, Ye
Pan, Huazheng
Zhang, Tao
Wu, Wen
Hu, Wenxin
Computation and Language
Artificial Intelligence
The goal of document-level relation extraction (RE) is to identify relations between entities that span multiple sentences. Recently, incomplete labeling in document-level RE has received increasing attention, and some studies have used methods such as positive-unlabeled learning to tackle this issue, but there is still a lot of room for improvement. Motivated by this, we propose a positive-augmentation and positive-mixup positive-unlabeled metric learning framework (P3M). Specifically, we formulate document-level RE as a metric learning problem. We aim to pull the distance closer between entity pair embedding and their corresponding relation embedding, while pushing it farther away from the none-class relation embedding. Additionally, we adapt the positive-unlabeled learning to this loss objective. In order to improve the generalizability of the model, we use dropout to augment positive samples and propose a positive-none-class mixup method. Extensive experiments show that P3M improves the F1 score by approximately 4-10 points in document-level RE with incomplete labeling, and achieves state-of-the-art results in fully labeled scenarios. Furthermore, P3M has also demonstrated robustness to prior estimation bias in incomplete labeled scenarios.
title A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2306.14806