Rewarding Coreference Resolvers for Being Consistent with World Knowledge

Autor: Rahul Aralikatte, Chen Qiu, Ana Valeria Gonzalez, Anders B. Sandholm, Heather C. Lent, Daniel Herschcovich, Anders Søgaard, Michael Ringaard

Publikováno v: Aralikatte, R, Lent, H, Gonzalez, A V, Herschcovich, D, Qiu, C, Sandholm, A, Ringaard, M & Søgaard, A 2019, Rewarding Coreference Resolvers for Being Consistent with World Knowledge . in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) . Association for Computational Linguistics, pp. 1229-1235, Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 01/11/2019 . https://doi.org/10.18653/v1/D19-1118
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
EMNLP/IJCNLP (1)

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 inp

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1710950f3ecfbb39d53f8abea92b7767
https://curis.ku.dk/ws/files/239862441/OA_Rewarding_Coreference_Resolvers_for_Being_Consistent.pdf