TDRE: A Tensor Decomposition Based Approach for Relation Extraction

TL;DR

TDRE introduces a tensor decomposition approach for relation extraction that efficiently models relation types and reduces redundant triplet extraction, outperforming existing methods on benchmark datasets.

Contribution

The paper proposes a novel tensor decomposition based method for relation extraction that effectively handles overlapping triplets and reduces unnecessary computations.

Findings

Outperforms strong baselines on NYT, CoNLL04, and ADE datasets.

Effectively extracts overlapping triplets with reduced redundancy.

Utilizes tensor decomposition to omit unpredicted relation types.

Abstract

Extracting entity pairs along with relation types from unstructured texts is a fundamental subtask of information extraction. Most existing joint models rely on fine-grained labeling scheme or focus on shared embedding parameters. These methods directly model the joint probability of multi-labeled triplets, which suffer from extracting redundant triplets with all relation types. However, each sentence may contain very few relation types. In this paper, we first model the final triplet extraction result as a three-order tensor of word-to-word pairs enriched with each relation type. And in order to obtain the sentence contained relations, we introduce an independent but joint training relation classification module. The tensor decomposition strategy is finally utilized to decompose the triplet tensor with predicted relational components which omits the calculations for unpredicted relation types. According to effective decomposition methods, we propose the Tensor Decomposition based Relation Extraction (TDRE) approach which is able to extract overlapping triplets and avoid detecting unnecessary entity pairs. Experiments on benchmark datasets NYT, CoNLL04 and ADE datasets demonstrate that the proposed method outperforms existing strong baselines.