Jointly Modeling Hierarchical and Horizontal Features for Relational Triple Extraction

TL;DR

This paper introduces a novel joint modeling framework that leverages hierarchical and horizontal feature interactions for improved relational triple extraction, utilizing multi-task learning with entity and relation extraction tasks.

Contribution

It proposes an entity-enhanced dual tagging framework that effectively models entity and relation features through shared parameters and auxiliary tasks without breaking joint decoding.

Findings

Outperforms state-of-the-art methods on NYT benchmark

Effectively models hierarchical and horizontal feature interactions

Utilizes multi-task learning for improved entity and relation extraction

Abstract

Recent works on relational triple extraction have shown the superiority of jointly extracting entities and relations over the pipelined extraction manner. However, most existing joint models fail to balance the modeling of entity features and the joint decoding strategy, and thus the interactions between the entity level and triple level are not fully investigated. In this work, we first introduce the hierarchical dependency and horizontal commonality between the two levels, and then propose an entity-enhanced dual tagging framework that enables the triple extraction (TE) task to utilize such interactions with self-learned entity features through an auxiliary entity extraction (EE) task, without breaking the joint decoding of relational triples. Specifically, we align the EE and TE tasks in a position-wise manner by formulating them as two sequence labeling problems with identical encoder-decoder structure. Moreover, the two tasks are organized in a carefully designed parameter sharing setting so that the learned entity features could be naturally shared via multi-task learning. Empirical experiments on the NYT benchmark demonstrate the effectiveness of the proposed framework compared to the state-of-the-art methods.