TPN: Transferable Proto-Learning Network towards Few-shot Document-Level Relation Extraction

TL;DR

This paper introduces TPN, a novel transferable proto-learning network designed to improve few-shot document-level relation extraction across domains by enhancing relation representations, mitigating NOTA bias, and employing virtual adversarial training.

Contribution

The paper presents a new TPN model with hybrid encoding, adaptive NOTA prototype learning, dynamic confidence calibration, and VAT, significantly improving cross-domain few-shot relation extraction performance.

Findings

Outperforms state-of-the-art methods on FREDo and ReFREDo datasets.

Achieves comparable results with about half the parameters of existing models.

Effectively mitigates NOTA bias and enhances cross-domain transferability.

Abstract

Few-shot document-level relation extraction suffers from poor performance due to the challenging cross-domain transferability of NOTA (none-of-the-above) relation representation. In this paper, we introduce a Transferable Proto-Learning Network (TPN) to address the challenging issue. It comprises three core components: Hybrid Encoder hierarchically encodes semantic content of input text combined with attention information to enhance the relation representations. As a plug-and-play module for Out-of-Domain (OOD) Detection, Transferable Proto-Learner computes NOTA prototype through an adaptive learnable block, effectively mitigating NOTA bias across various domains. Dynamic Weighting Calibrator detects relation-specific classification confidence, serving as dynamic weights to calibrate the NOTA-dominant loss function. Finally, to bolster the model's cross-domain performance, we complement it with virtual adversarial training (VAT). We conduct extensive experimental analyses on FREDo and ReFREDo, demonstrating the superiority of TPN. Compared to state-of-the-art methods, our approach achieves competitive performance with approximately half the parameter size. Data and code are available at https://github.com/EchoDreamer/TPN.