SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.04497 · EMNLP · 2022

Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation

Peiyi Wang, Zhifang Sui, Yifan Song, Sujian Li, Tianyu Liu, Yunbo Cao, Binghuai Lin

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Continual relation extraction (CRE) aims to continually learn new relations from a classincremental data stream. CRE model usually suffers from catastrophic forgetting problem, i.e., the performance of old relations seriously degrades when the model learns new relations. Most previous work attributes catastrophic forgetting to the corruption of the learned representations as new relations come, with an implicit assumption that the CRE models have adequately learned the old relations. In this paper, through empirical studies we argue that this assumption may not hold, and an important reason for catastrophic forgetting is that the learned representations do not have good robustness against the appearance of analogous relations in the subsequent learning process. To address this issue, we encourage the model to learn more precise and robust representations through a simple yet effective adversarial class augmentation mechanism (ACA), which is easy to implement and model-agnostic. Experimental results show that ACA can consistently improve the performance of state-of-theart CRE models on two popular benchmarks. Our code is available at https://github. com/Wangpeiyi9979/ACA.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2210.04497")
get_code_for_paper("2210.04497")
have("2210.04497")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2210.04497.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2210.04497.svg)](https://syntology.ai/paper/2210.04497)

Connect an agent — have() is free.