Existing datasets for natural language inference (NLI) have propelled research on language understanding. We propose a new method for automatically deriving NLI datasets from the growing abundance of large-scale question answering datasets. Our approach hinges on learning a sentence transformation model which converts question-answer pairs into their declarative forms. Despite being primarily trained on a single QA dataset, we show that it can be successfully applied to a variety of other QA resources. Using this system, we automatically derive a new freely available dataset of over 500k NLI examples (QA-NLI), and show that it exhibits a wide range of inference phenomena rarely seen in previous NLI datasets.
@article{arxiv.1809.02922,
title = {Transforming Question Answering Datasets Into Natural Language Inference Datasets},
author = {Dorottya Demszky and Kelvin Guu and Percy Liang},
journal= {arXiv preprint arXiv:1809.02922},
year = {2018}
}