We present WikiReading, a large-scale natural language understanding task and publicly-available dataset with 18 million instances. The task is to predict textual values from the structured knowledge base Wikidata by reading the text of the corresponding Wikipedia articles. The task contains a rich variety of challenging classification and extraction sub-tasks, making it well-suited for end-to-end models such as deep neural networks (DNNs). We compare various state-of-the-art DNN-based architectures for document classification, information extraction, and question answering. We find that models supporting a rich answer space, such as word or character sequences, perform best. Our best-performing model, a word-level sequence to sequence model with a mechanism to copy out-of-vocabulary words, obtains an accuracy of 71.8%.
@article{arxiv.1608.03542,
title = {WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia},
author = {Daniel Hewlett and Alexandre Lacoste and Llion Jones and Illia Polosukhin and Andrew Fandrianto and Jay Han and Matthew Kelcey and David Berthelot},
journal= {arXiv preprint arXiv:1608.03542},
year = {2017}
}