English

Improving Natural Language Inference Using External Knowledge in the Science Questions Domain

Artificial Intelligence 2018-11-21 v2 Computation and Language Machine Learning

Abstract

Natural Language Inference (NLI) is fundamental to many Natural Language Processing (NLP) applications including semantic search and question answering. The NLI problem has gained significant attention thanks to the release of large scale, challenging datasets. Present approaches to the problem largely focus on learning-based methods that use only textual information in order to classify whether a given premise entails, contradicts, or is neutral with respect to a given hypothesis. Surprisingly, the use of methods based on structured knowledge -- a central topic in artificial intelligence -- has not received much attention vis-a-vis the NLI problem. While there are many open knowledge bases that contain various types of reasoning information, their use for NLI has not been well explored. To address this, we present a combination of techniques that harness knowledge graphs to improve performance on the NLI problem in the science questions domain. We present the results of applying our techniques on text, graph, and text-to-graph based models, and discuss implications for the use of external knowledge in solving the NLI problem. Our model achieves the new state-of-the-art performance on the NLI problem over the SciTail science questions dataset.

Keywords

Cite

@article{arxiv.1809.05724,
  title  = {Improving Natural Language Inference Using External Knowledge in the Science Questions Domain},
  author = {Xiaoyan Wang and Pavan Kapanipathi and Ryan Musa and Mo Yu and Kartik Talamadupula and Ibrahim Abdelaziz and Maria Chang and Achille Fokoue and Bassem Makni and Nicholas Mattei and Michael Witbrock},
  journal= {arXiv preprint arXiv:1809.05724},
  year   = {2018}
}

Comments

9 pages, 3 figures, 5 tables

R2 v1 2026-06-23T04:07:24.451Z