%0 Conference Proceedings %T Rewarding Coreference Resolvers for Being Consistent with World Knowledge %A Aralikatte, Rahul %A Lent, Heather %A Gonzalez, Ana Valeria %A Hershcovich, Daniel %A Qiu, Chen %A Sandholm, Anders %A Ringaard, Michael %A Søgaard, Anders %Y Inui, Kentaro %Y Jiang, Jing %Y Ng, Vincent %Y Wan, Xiaojun %S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) %D 2019 %8 November %I Association for Computational Linguistics %C Hong Kong, China %F aralikatte-etal-2019-rewarding %X Unresolved coreference is a bottleneck for relation extraction, and high-quality coreference resolvers may produce an output that makes it a lot easier to extract knowledge triples. We show how to improve coreference resolvers by forwarding their input to a relation extraction system and reward the resolvers for producing triples that are found in knowledge bases. Since relation extraction systems can rely on different forms of supervision and be biased in different ways, we obtain the best performance, improving over the state of the art, using multi-task reinforcement learning. %R 10.18653/v1/D19-1118 %U https://aclanthology.org/D19-1118 %U https://doi.org/10.18653/v1/D19-1118 %P 1229-1235