Rewarding Coreference Resolvers for Being Consistent with World Knowledge [article]

Rahul Aralikatte, Heather Lent, Ana Valeria Gonzalez, Daniel Hershcovich, Chen Qiu, Anders Sandholm, Michael Ringaard, Anders Søgaard
2019 arXiv   pre-print
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
more » ... ormance, improving over the state of the art, using multi-task reinforcement learning.
arXiv:1909.02392v2 fatcat:q6jgtusjkbh3rferfxlsecbvzi