Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs

Proceedings of the 28th International Conference on Computational Linguistics, pages 6498–6508 Barcelona, Spain (Online), December 8-13, 2020 6498 Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs Zikang Wang1,2, Linjing Li1,2,3, and Daniel Zeng1,2,3 1State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China 2University of Chinese Academy of Sciences, Beijing, 100049, China 3Shenzhen Artificial Intelligence and Data Science Institute (Longhua), Shenzhen, China {wangzikang2016, linjing.li, dajun.zeng}@ia.ac.cn Abstract Natural Language Inference (NLI) is a vital task in natural language processing. It aims to iden- tify the logical relationship between two sentences. Most of the existing approaches make such inference based on semantic knowledge obtained through training corpus. The adoption of back- ground knowledge is rarely seen or limited to a few specific types. In this paper, we propose a novel Knowledge Graph-enhanced NLI (KGNLI) model to leverage the usage of background knowledge stored in knowledge graphs in the field of NLI. KGNLI model consists of three com- ponents: a semantic-relation representation module, a knowledge-relation representation module, and a label prediction module. Different from previous methods, various kinds of background knowledge can be flexibly combined in the proposed KGNLI model. Experiments on four bench- marks, SNLI, MultiNLI, SciTail, and BNLI, validate the effectiveness of our model. 1 Introduction Natural Language Inference (NLI) is a fundamental yet challenging task for natural language understand- ing. NLI aims to determine whether the logical relationship between a premise p and a hypothesis h is entailment, neutral, or contradiction. NLI requires reasoning and inference abilities which are crucial for artificial intelligence system. Recent years have witnessed a large improvement in NLI models because of the release of several large-scale corpora, such as SNLI (Bowman et al., 2015) and MultiNLI (Williams et al., 2018). These datasets enable various deep learning models to achieve state-of-the-art performances (Chen et al., 2017; Chen et al., 2018; Pan et al., 2018; Ghaeini et al., 2018). Most of the existing NLI models are based on cross sentence attention (Chen et al., 2017). They learn alignments according to the attention between premises and hypotheses. The resulting alignments and semantic representations of sentences are aggregated and fed into a multilayer feed-forward neu- ral network to judge logical relationships. However, only semantic knowledge between premises and hypotheses are utilized in most of these models. Background knowledge can be utilized to facilitate inference as shown in Fig. 1. For the sentences located in the left part of Fig. 1, the logical relationship between the Premise and the Hypothsis largely depends on the relationship between “piano” and “music”. However, the latter is not explicitly expressed in the sentences per se. The right part of Fig. 1 is a part of a large knowledge graph, in which paths between “piano” and “music” represent background knowledge that can be utilized to determine the relationship of the sentence pair. Previous work (Chen et al., 2018) shows that NLI models can benefit from leveraging external knowledge. But only restricted kinds of knowledge are …

Content truncated to 500 words