We present a new architecture for storing and accessing entity mentions during online text processing. While reading the text, entity references are identified, and may be stored by either updating or overwriting a cell in a fixed-length memory. The update operation implies coreference with the other mentions that are stored in the same cell; the overwrite operation causes these mentions to be forgotten. By encoding the memory operations as differentiable gates, it is possible to train the model end-to-end, using both a supervised anaphora resolution objective as well as a supplementary language modeling objective. Evaluation on a dataset of pronoun-name anaphora demonstrates strong performance with purely incremental text processing.
@article{arxiv.1902.01541,
title = {The Referential Reader: A Recurrent Entity Network for Anaphora Resolution},
author = {Fei Liu and Luke Zettlemoyer and Jacob Eisenstein},
journal= {arXiv preprint arXiv:1902.01541},
year = {2019}
}
Comments
Published at the 57th Annual Meeting of the Association for Computational Linguistics (ACL) 2019. Source code available at: https://github.com/liufly/refreader