Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks

TL;DR

This paper introduces a method that enhances textual entailment models by integrating external knowledge graphs through personalized PageRank and graph convolutional networks, significantly improving accuracy especially on challenging datasets.

Contribution

The paper proposes a novel approach combining personalized PageRank and graph convolutional networks to effectively encode knowledge graphs for textual entailment tasks.

Findings

Improved accuracy on multiple datasets including BreakingNLI.

Significant 5-20% accuracy boost on challenging entailment datasets.

Effective encoding of large, noisy knowledge graphs enhances model performance.

Abstract

Textual entailment is a fundamental task in natural language processing. Most approaches for solving the problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task. However, the proposed models do not fully exploit the information in the usually large and noisy KGs, and it is not clear how it can be effectively encoded to be useful for entailment. We present an approach that complements text-based entailment models with information from KGs by (1) using Personalized PageR- ank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture KG structure. Our technique extends the capability of text models exploiting structural and semantic information found in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps improve prediction accuracy. This is particularly evident in the challenging BreakingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models.