Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning

TL;DR

This paper introduces DIRECT, a graph-oriented relational fact extraction model that uses adaptive multi-task learning to improve accuracy and address common challenges, outperforming existing state-of-the-art methods.

Contribution

The paper proposes a novel graph-oriented analytical framework and an adaptive multi-task learning strategy for relational fact extraction.

Findings

Outperforms state-of-the-art models on benchmark datasets

Effectively alleviates error propagation issues

Demonstrates robustness across different datasets

Abstract

Relational fact extraction aims to extract semantic triplets from unstructured text. In this work, we show that all of the relational fact extraction models can be organized according to a graph-oriented analytical perspective. An efficient model, aDjacency lIst oRiented rElational faCT (DIRECT), is proposed based on this analytical framework. To alleviate challenges of error propagation and sub-task loss equilibrium, DIRECT employs a novel adaptive multi-task learning strategy with dynamic sub-task loss balancing. Extensive experiments are conducted on two benchmark datasets, and results prove that the proposed model outperforms a series of state-of-the-art (SoTA) models for relational triplet extraction.