Sentence-Incremental Neural Coreference Resolution

Abstract

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 networkbased 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 6.8 F1 on the CODI-CRAC 2021 corpus. In a conventional coreference setup, our system achieves 76.3 F1 on OntoNotes and 45.5 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. 1

Investigating Multilingual Coreference Resolution by Universal Annotations

“…Coreference resolution is the task to identify expressions in a given text that refer to the same entity. While considerable progress has been made in coreference resolution for English (Lee et al, 2017(Lee et al, , 2018Joshi et al, 2019Joshi et al, , 2020Kirstain et al, 2021;Grenander et al, 2022), extending this task to multiple languages presents significant challenges due to the linguistic diversity and complexity of different languages. The multilingual coreference resolution (MCR) task Pradhan et al, 2012) focuses on developing a general and robust system that can effectively handle multiple languages and a wide range of coreference phenomena (e.g., pronoun-drop).…”