Sentence-Incremental Neural Coreference Resolution
This work addresses computational efficiency for NLP researchers and practitioners by bridging gaps between non-incremental and incremental coreference models, though it is incremental in nature.
The paper tackles the problem of high computational cost in coreference resolution by proposing a sentence-incremental neural system that builds clusters incrementally, outperforming state-of-the-art methods by 2 F1 on OntoNotes and 7 F1 on CODI-CRAC 2021 in an incremental setting.
We propose a sentence-incremental neural coreference resolution system which incrementally builds clusters after marking mention boundaries in a shift-reduce method. The system is aimed at bridging two recent approaches at coreference resolution: (1) state-of-the-art non-incremental models that incur quadratic complexity in document length with high computational cost, and (2) memory network-based models which operate incrementally but do not generalize beyond pronouns. For comparison, we simulate an incremental setting by constraining non-incremental systems to form partial coreference chains before observing new sentences. In this setting, our system outperforms comparable state-of-the-art methods by 2 F1 on OntoNotes and 7 F1 on the CODI-CRAC 2021 corpus. In a conventional coreference setup, our system achieves 76.3 F1 on OntoNotes and 45.8 F1 on CODI-CRAC 2021, which is comparable to state-of-the-art baselines. We also analyze variations of our system and show that the degree of incrementality in the encoder has a surprisingly large effect on the resulting performance.