KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction
TL
TL;DR
The KGPool method dynamically expands the context with additional facts from the KG, and learns the representation of these facts (entity alias, entity descriptions, etc.) using neural methods, supplementing the sentential context.
Abstract
We present a novel method for relation extraction (RE) from a single sentence, mapping the sentence and two given entities to a canonical fact in a knowledge graph (KG). Especially in this presumed sentential RE setting, the context of a single sentence is often sparse. This paper introduces the KGPool method to address this sparsity, dynamically expanding the context with additional facts from the KG. It learns the representation of these facts (entity alias, entity descriptions, etc.) using neural methods, supplementing the sentential context. Unlike existing methods that statically use all expanded facts, KGPool conditions this expansion on the sentence. We study the efficacy of KGPool by evaluating it with different neural models and KGs (Wikidata and NYT Freebase). Our experimental evaluation on standard datasets shows that by feeding the KGPool representation into a Graph Neural Network, the overall method is significantly more accurate than state-of-the-art methods.
References43 items
1
Dynamic Context Selection for Document-level Neural Machine Translation via Reinforcement Learning
2
Contextual Knowledge Selection and Embedding towards Enhanced Pre-Trained Language Models
3
RECON: Relation Extraction using Knowledge Graph Context in a Graph Neural Network
4
Evaluating the Impact of Knowledge Graph Context on Entity Disambiguation Models
5