PRiSM: Enhancing Low-Resource Document-Level Relation Extraction with Relation-Aware Score Calibration
Document-level relation extraction (DocRE) aims to extract relations of all entity pairs in a document. A key challenge in DocRE is the cost of annotating such data which requires intensive human effort. Thus, we investigate the case of DocRE in a low-resource setting, and we find that existing mode...
Gespeichert in:
Hauptverfasser: | , , |
---|---|
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Document-level relation extraction (DocRE) aims to extract relations of all
entity pairs in a document. A key challenge in DocRE is the cost of annotating
such data which requires intensive human effort. Thus, we investigate the case
of DocRE in a low-resource setting, and we find that existing models trained on
low data overestimate the NA ("no relation") label, causing limited
performance. In this work, we approach the problem from a calibration
perspective and propose PRiSM, which learns to adapt logits based on relation
semantic information. We evaluate our method on three DocRE datasets and
demonstrate that integrating existing models with PRiSM improves performance by
as much as 26.38 F1 score, while the calibration error drops as much as 36
times when trained with about 3% of data. The code is publicly available at
https://github.com/brightjade/PRiSM. |
---|---|
DOI: | 10.48550/arxiv.2309.13869 |