Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Incremental Neural Coreference Resolution in Constant Memory

About

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.

Patrick Xia, Jo\~ao Sedoc, Benjamin Van Durme• 2020

Related benchmarks

TaskDatasetResultRank
Coreference ResolutionCoNLL English 2012 (test)
MUC F1 Score85.3
114
Coreference ResolutionOntoNotes
MUC85.3
23
Coreference ResolutionEnglish OntoNotes 5.0 (test)--
18
Coreference ResolutionOntoNotes 5.0 (dev)
CoNLL F179.7
13
Showing 4 of 4 rows

Other info

Follow for update