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

06/03/2021
by   Fubang Zhao, et al.
0

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.

READ FULL TEXT
08/23/2019

Joint Extraction of Entities and Relations with a Hierarchical Multi-task Tagging Model

Entity extraction and relation extraction are two indispensable building...
10/18/2021

A Bayesian approach to multi-task learning with network lasso

Network lasso is a method for solving a multi-task learning problem thro...
08/16/2017

Multi-task Neural Network for Non-discrete Attribute Prediction in Knowledge Graphs

Many popular knowledge graphs such as Freebase, YAGO or DBPedia maintain...
12/17/2019

A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction

Aspect-based sentiment analysis (ABSA) task is a multi-grained task of n...
09/11/2020

Learning an Interpretable Graph Structure in Multi-Task Learning

We present a novel methodology to jointly perform multi-task learning an...
05/11/2022

Relational Triple Extraction: One Step is Enough

Extracting relational triples from unstructured text is an essential tas...
08/02/2022

Curvature-informed multi-task learning for graph networks

Properties of interest for crystals and molecules, such as band gap, ela...