Abstract
Coreference resolution is the task of finding expressions that refer to the same entity in a text. Coreference models are generally trained on monolingual annotated data but annotating coreference is expensive and challenging. Hardmeier et al. (2013) have shown that parallel data contains latent anaphoric knowledge, but it has not been explored in end-to-end neural models yet. In this paper, we propose a simple yet effective model to exploit coreference knowledge from parallel data. In addition to the conventional modules learning coreference from annotations, we introduce an unsupervised module to capture cross-lingual coreference knowledge. Our proposed cross-lingual model achieves consistent improvements, up to 1.74 percentage points, on the OntoNotes 5.0 English dataset using 9 different synthetic parallel datasets. These experimental results confirm that parallel data can provide additional coreference knowledge which is beneficial to coreference resolution tasks.
Originalsprog | Engelsk |
---|---|
Titel | Findings of the Association for Computational Linguistics: ACL 2023 |
Redaktører | Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki |
Udgivelsessted | Canada |
Forlag | Association for Computational Linguistics |
Publikationsdato | jul. 2023 |
Udgave | 2023 |
Sider | 3162-3171 |
ISBN (Elektronisk) | 978-1-959429-62-3 |
DOI | |
Status | Udgivet - jul. 2023 |
Emneord
- Coreference Resolution
- Parallel Data
- Unsupervised Learning
- Cross-lingual Coreference
- Neural Models
- Coreference Knowledge
- Synthetic Datasets
- Anaphoric Knowledge
- OntoNotes 5.0
- Monolingual Annotated Data