Seq2seq is All You Need for Coreference Resolution
This work challenges the need for complex, task-specific models in coreference resolution, potentially simplifying NLP pipelines.
The authors tackled coreference resolution by finetuning a pretrained seq2seq transformer to map documents to tagged sequences, showing that this simple approach outperforms or matches state-of-the-art task-specific models on multiple datasets.
Existing works on coreference resolution suggest that task-specific models are necessary to achieve state-of-the-art performance. In this work, we present compelling evidence that such models are not necessary. We finetune a pretrained seq2seq transformer to map an input document to a tagged sequence encoding the coreference annotation. Despite the extreme simplicity, our model outperforms or closely matches the best coreference systems in the literature on an array of datasets. We also propose an especially simple seq2seq approach that generates only tagged spans rather than the spans interleaved with the original text. Our analysis shows that the model size, the amount of supervision, and the choice of sequence representations are key factors in performance.