Rewarding Coreference Resolvers for Being Consistent with World Knowledge
This work addresses a specific bottleneck in relation extraction for NLP applications, representing an incremental improvement.
The paper tackled the problem of unresolved coreference as a bottleneck for relation extraction by improving coreference resolvers through rewarding them for producing knowledge triples found in knowledge bases, achieving state-of-the-art performance.
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.