End-to-end Neural Coreference Resolution
This solves the problem of coreference resolution for NLP applications by eliminating the need for parsers or hand-engineered detectors, though it is incremental in improving existing methods.
The authors tackled coreference resolution by introducing the first end-to-end model that directly considers all spans as potential mentions, achieving state-of-the-art performance with a 1.5 F1 gain on OntoNotes and 3.1 F1 with an ensemble.
We introduce the first end-to-end coreference resolution model and show that it significantly outperforms all previous work without using a syntactic parser or hand-engineered mention detector. The key idea is to directly consider all spans in a document as potential mentions and learn distributions over possible antecedents for each. The model computes span embeddings that combine context-dependent boundary representations with a head-finding attention mechanism. It is trained to maximize the marginal likelihood of gold antecedent spans from coreference clusters and is factored to enable aggressive pruning of potential mentions. Experiments demonstrate state-of-the-art performance, with a gain of 1.5 F1 on the OntoNotes benchmark and by 3.1 F1 using a 5-model ensemble, despite the fact that this is the first approach to be successfully trained with no external resources.