Mutually Guided Few-shot Learning for Relational Triple Extraction

TL;DR

This paper introduces MG-FTE, a novel few-shot learning framework for extracting relational triples from text, using mutually guiding decoders and a fusion module to improve performance in low-data scenarios.

Contribution

The paper proposes a new mutually guided few-shot learning framework with a proto-level fusion module for relational triple extraction, addressing cross-domain challenges.

Findings

Outperforms state-of-the-art by 12.6 F1 on FewRel 1.0

Achieves 20.5 F1 improvement on FewRel 2.0

Effective in cross-domain few-shot triple extraction

Abstract

Knowledge graphs (KGs), containing many entity-relation-entity triples, provide rich information for downstream applications. Although extracting triples from unstructured texts has been widely explored, most of them require a large number of labeled instances. The performance will drop dramatically when only few labeled data are available. To tackle this problem, we propose the Mutually Guided Few-shot learning framework for Relational Triple Extraction (MG-FTE). Specifically, our method consists of an entity-guided relation proto-decoder to classify the relations firstly and a relation-guided entity proto-decoder to extract entities based on the classified relations. To draw the connection between entity and relation, we design a proto-level fusion module to boost the performance of both entity extraction and relation classification. Moreover, a new cross-domain few-shot triple extraction task is introduced. Extensive experiments show that our method outperforms many state-of-the-art methods by 12.6 F1 score on FewRel 1.0 (single-domain) and 20.5 F1 score on FewRel 2.0 (cross-domain).