Select and Augment: Enhanced Dense Retrieval Knowledge Graph Augmentation

TL;DR

This paper introduces a multi-task framework that selectively retrieves and augments knowledge graph entities with multiple relevant text descriptions, significantly improving link prediction performance over traditional methods.

Contribution

It proposes a novel multi-task approach that dynamically selects multiple relevant descriptions for KG entities, enhancing embedding quality beyond single-description methods.

Findings

Achieved 5.5% increase in MRR for link prediction

Achieved 3.5% increase in Hits@10

Outperforms traditional CNN-based text augmentation methods

Abstract

Injecting textual information into knowledge graph (KG) entity representations has been a worthwhile expedition in terms of improving performance in KG oriented tasks within the NLP community. External knowledge often adopted to enhance KG embeddings ranges from semantically rich lexical dependency parsed features to a set of relevant key words to entire text descriptions supplied from an external corpus such as wikipedia and many more. Despite the gains this innovation (Text-enhanced KG embeddings) has made, the proposal in this work suggests that it can be improved even further. Instead of using a single text description (which would not sufficiently represent an entity because of the inherent lexical ambiguity of text), we propose a multi-task framework that jointly selects a set of text descriptions relevant to KG entities as well as align or augment KG embeddings with text descriptions. Different from prior work that plugs formal entity descriptions declared in knowledge bases, this framework leverages a retriever model to selectively identify richer or highly relevant text descriptions to use in augmenting entities. Furthermore, the framework treats the number of descriptions to use in augmentation process as a parameter, which allows the flexibility of enumerating across several numbers before identifying an appropriate number. Experiment results for Link Prediction demonstrate a 5.5% and 3.5% percentage increase in the Mean Reciprocal Rank (MRR) and Hits@10 scores respectively, in comparison to text-enhanced knowledge graph augmentation methods using traditional CNNs.