Rewarding Coreference Resolvers for Being Consistent with World Knowledge
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Dokumenter
- OA-Rewarding Coreference Resolvers for Being Consistent
Forlagets udgivne version, 467 KB, PDF-dokument
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.
Originalsprog | Engelsk |
---|---|
Titel | Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
Forlag | Association for Computational Linguistics |
Publikationsdato | 2019 |
Sider | 1229-1235 |
DOI | |
Status | Udgivet - 2019 |
Begivenhed | 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) - Hong Kong, China Varighed: 1 nov. 2019 → 1 nov. 2019 |
Konference
Konference | 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) |
---|---|
Lokation | Hong Kong, China |
Periode | 01/11/2019 → 01/11/2019 |
Antal downloads er baseret på statistik fra Google Scholar og www.ku.dk
Ingen data tilgængelig
ID: 239862438