Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks (original) (raw)

2020, Proceedings of the ... AAAI Conference on Artificial Intelligence

Textual entailment is a fundamental task in natural language processing. Most approaches for solving this 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 PageRank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture the structural and semantic information in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps the model to be robust and improves prediction accuracy. This is particularly evident in the challenging Break-ingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models. 1 Introduction Given two natural language sentences, a premise P and a hypothesis H, the textual entailment task-also known as natural language inference (NLI)-consists of determining whether the premise entails, contradicts, or is neutral with respect to the given hypothesis (MacCartney and Manning 2009). In practice, this means that textual entailment is characterized as either a threeclass (ENTAILS/NEUTRAL/CONTRADICTS) or a two-class (ENTAILS/NEUTRAL) classification problem (Bowman et al. 2015; Khot, Sabharwal, and Clark 2018). Performance on the textual entailment task can be an indicator of whether a system, and the models it uses, are able to reason over text. This has tremendous value for modeling the complexities of human-level natural language understanding, and in aiding systems tuned for downstream tasks such as question answering (Harabagiu and Hickl 2006).