Coreference Resolution without Span Representations
This work provides a more memory-efficient approach to coreference resolution, which is beneficial for researchers and practitioners working with long documents or limited computational resources.
This paper addresses the memory footprint issue in coreference resolution models by eliminating the need for span and span-pair representations. The proposed lightweight model achieves competitive performance compared to the current standard, while being simpler and more efficient.
The introduction of pretrained language models has reduced many complex task-specific NLP models to simple lightweight layers. An exception to this trend is coreference resolution, where a sophisticated task-specific model is appended to a pretrained transformer encoder. While highly effective, the model has a very large memory footprint -- primarily due to dynamically-constructed span and span-pair representations -- which hinders the processing of complete documents and the ability to train on multiple instances in a single batch. We introduce a lightweight end-to-end coreference model that removes the dependency on span representations, handcrafted features, and heuristics. Our model performs competitively with the current standard model, while being simpler and more efficient.