Standard
Rewarding Coreference Resolvers for Being Consistent with World Knowledge. / Aralikatte, Rahul; Lent, Heather; Gonzalez, Ana Valeria; Herschcovich, Daniel; Qiu, Chen; Sandholm, Anders; Ringaard, Michael; Søgaard, Anders.
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, 2019. s. 1229-1235.
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
Aralikatte, R, Lent, H
, Gonzalez, AV, Herschcovich, D, Qiu, C, Sandholm, A, Ringaard, M
& Søgaard, A 2019,
Rewarding Coreference Resolvers for Being Consistent with World Knowledge. i
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, s. 1229-1235, 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/D19-1118APA
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. I
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) (s. 1229-1235). Association for Computational Linguistics.
https://doi.org/10.18653/v1/D19-1118Vancouver
Aralikatte R, Lent H
, Gonzalez AV, Herschcovich D, Qiu C, Sandholm A o.a.
Rewarding Coreference Resolvers for Being Consistent with World Knowledge. I 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. 2019. s. 1229-1235
https://doi.org/10.18653/v1/D19-1118Author
Aralikatte, Rahul ; Lent, Heather ; Gonzalez, Ana Valeria ; Herschcovich, Daniel ; Qiu, Chen ; Sandholm, Anders ; Ringaard, Michael ; Søgaard, Anders. / Rewarding Coreference Resolvers for Being Consistent with World Knowledge. 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, 2019. s. 1229-1235
Bibtex
@inproceedings{2a8bea2259f444278b1cd21bfa54a516,
title = "Rewarding Coreference Resolvers for Being Consistent with World Knowledge",
abstract = "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.",
author = "Rahul Aralikatte and Heather Lent and Gonzalez, {Ana Valeria} and Daniel Herschcovich and Chen Qiu and Anders Sandholm and Michael Ringaard and Anders S{\o}gaard",
year = "2019",
doi = "10.18653/v1/D19-1118",
language = "English",
pages = "1229--1235",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
publisher = "Association for Computational Linguistics",
note = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) ; Conference date: 01-11-2019 Through 01-11-2019",
}
RIS
TY - GEN
T1 - Rewarding Coreference Resolvers for Being Consistent with World Knowledge
AU - Aralikatte, Rahul
AU - Lent, Heather
AU - Gonzalez, Ana Valeria
AU - Herschcovich, Daniel
AU - Qiu, Chen
AU - Sandholm, Anders
AU - Ringaard, Michael
AU - Søgaard, Anders
PY - 2019
Y1 - 2019
N2 - 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.
AB - 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.
U2 - 10.18653/v1/D19-1118
DO - 10.18653/v1/D19-1118
M3 - Article in proceedings
SP - 1229
EP - 1235
BT - Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
PB - Association for Computational Linguistics
T2 - Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Y2 - 1 November 2019 through 1 November 2019
ER -
