English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

The goal of document-level relation extraction (RE) is to identify relationsbetween entities that span multiple sentences. Recently, incomplete labeling indocument-level RE has received increasing attention, and some studies have usedmethods such as positive-unlabeled learning to tackle this issue, but there isstill a lot of room for improvement. Motivated by this, we propose apositive-augmentation and positive-mixup positive-unlabeled metric learningframework (P3M). Specifically, we formulate document-level RE as a metriclearning problem. We aim to pull the distance closer between entity pairembedding and their corresponding relation embedding, while pushing it fartheraway from the none-class relation embedding. Additionally, we adapt thepositive-unlabeled learning to this loss objective. In order to improve thegeneralizability of the model, we use dropout to augment positive samples andpropose a positive-none-class mixup method. Extensive experiments show that P3Mimproves the F1 score by approximately 4-10 points in document-level RE withincomplete labeling, and achieves state-of-the-art results in fully labeledscenarios. Furthermore, P3M has also demonstrated robustness to priorestimation bias in incomplete labeled scenarios.

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