Adjacency List Oriented Relational Fact Extraction via Adaptive Multi-task Learning
This work addresses relational triplet extraction for natural language processing, presenting an incremental improvement over existing methods.
The paper tackled relational fact extraction from unstructured text by proposing DIRECT, a model based on a graph-oriented analytical perspective with adaptive multi-task learning, which outperformed state-of-the-art models on two benchmark datasets.
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.