Incremental Neural Coreference Resolution in Constant Memory
This work addresses memory efficiency for coreference resolution, which is incremental as it adapts an existing high-performing model.
The paper tackled the problem of coreference resolution under fixed memory constraints by extending an incremental clustering algorithm with neural components, achieving a 0.3% relative loss in F1 on OntoNotes 5.0 while reducing memory usage to constant space.
We investigate modeling coreference resolution under a fixed memory constraint by extending an incremental clustering algorithm to utilize contextualized encoders and neural components. Given a new sentence, our end-to-end algorithm proposes and scores each mention span against explicit entity representations created from the earlier document context (if any). These spans are then used to update the entity's representations before being forgotten; we only retain a fixed set of salient entities throughout the document. In this work, we successfully convert a high-performing model (Joshi et al., 2020), asymptotically reducing its memory usage to constant space with only a 0.3% relative loss in F1 on OntoNotes 5.0.