Always the Best Fit: Adaptive Domain Gap Filling from Causal Perspective for Few-Shot Relation Extraction

Ge Bai, Chenji Lu, Jiaxiang Geng, Shilong Li, Yidong Shi, Xiyan Liu, Ying Liu, Zhang Zhang, Ruifang Liu

Submission Type: Regular Short Paper

Submission Track: Information Extraction

Submission Track 2: Language Modeling and Analysis of Language Models

Keywords: Cross domain, Causal Inference, Few-Shot, Relation Extraction

Abstract:

Cross-domain Relation Extraction aims to transfer knowledge from a source domain to a different target domain to address low-resource challenges. However, the semantic gap caused by data bias between domains is a major challenge, especially in few-shot scenarios.
Previous work has mainly focused on transferring knowledge between domains through shared feature representations without analyzing the impact of each factor that may produce data bias based on the characteristics of each domain.
This work takes a causal perspective and proposes a new framework CausalGF.
By constructing a unified structural causal model, we estimating the causal effects of factors such as syntactic structure, label distribution,and entities on the outcome.
CausalGF calculates the causal effects among the factors and adjusts them dynamically based on domain characteristics, enabling adaptive gap filling.
Our experiments show that our approach better fills the domain gap, yielding significantly better results on the cross-domain few-shot relation extraction task.

Submission Number: 29