# Rewarding Coreference Resolvers for Being Consistent with World Knowledge

arXiv: https://arxiv.org/abs/1909.02392 · HTML: https://mlsanity.com/paper/1909.02392/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 5 of 5)

- [On Generalization in Coreference Resolution](https://mlsanity.com/paper/2109.09667/) (2021)
- [Compositional Generalization in Multilingual Semantic Parsing over Wikidata](https://mlsanity.com/paper/2108.03509/) (2021)
- [Major Entity Identification: A Generalizable Alternative to Coreference Resolution](https://mlsanity.com/paper/2406.14654/) (2024)
- [The KITMUS Test: Evaluating Knowledge Integration from Multiple Sources in Natural Language Understanding Systems](https://mlsanity.com/paper/2212.08192/) (2022)
- [Persian Pronoun Resolution: Leveraging Neural Networks and Language Models](https://mlsanity.com/paper/2405.10714/) (2024)

## Abstract (arXiv)

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.