Word-Level Coreference Resolution
This addresses a computational bottleneck in coreference resolution for NLP researchers, offering an incremental improvement in efficiency.
The paper tackles the computational inefficiency of span-based coreference resolution by proposing a word-level approach that reduces complexity from O(n^4) to O(n^2), allowing consideration of all potential mentions without pruning, and it performs competitively with recent systems on the OntoNotes benchmark.
Recent coreference resolution models rely heavily on span representations to find coreference links between word spans. As the number of spans is $O(n^2)$ in the length of text and the number of potential links is $O(n^4)$, various pruning techniques are necessary to make this approach computationally feasible. We propose instead to consider coreference links between individual words rather than word spans and then reconstruct the word spans. This reduces the complexity of the coreference model to $O(n^2)$ and allows it to consider all potential mentions without pruning any of them out. We also demonstrate that, with these changes, SpanBERT for coreference resolution will be significantly outperformed by RoBERTa. While being highly efficient, our model performs competitively with recent coreference resolution systems on the OntoNotes benchmark.