# Joint Coreference Resolution for Zeros and non-Zeros in Arabic

arXiv: https://arxiv.org/abs/2210.12169 · HTML: https://mlsanity.com/paper/2210.12169/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 36 references that are in the map.
- First posted on arXiv 21 Oct 2022.

## Builds on (most cited first, 6 of 6)

- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Neural Coreference Resolution for Arabic](https://mlsanity.com/paper/2011.00286/) (2020)
- [A Deep Neural Network for Chinese Zero Pronoun Resolution](https://mlsanity.com/paper/1604.05800/) (2016)
- [Pseudo Zero Pronoun Resolution Improves Zero Anaphora Resolution](https://mlsanity.com/paper/2104.07425/) (2021)
- [Generating and Exploiting Large-scale Pseudo Training Data for Zero Pronoun Resolution](https://mlsanity.com/paper/1606.01603/) (2016)

## Built on by (most cited first, 1 of 1)

- [ThaiCoref: Thai Coreference Resolution Dataset](https://mlsanity.com/paper/2406.06000/) (2024)

## Abstract (arXiv)

Most existing proposals about anaphoric zero pronoun (AZP) resolution regard full mention coreference and AZP resolution as two independent tasks, even though the two tasks are clearly related. The main issues that need tackling to develop a joint model for zero and non-zero mentions are the difference between the two types of arguments (zero pronouns, being null, provide no nominal information) and the lack of annotated datasets of a suitable size in which both types of arguments are annotated for languages other than Chinese and Japanese. In this paper, we introduce two architectures for jointly resolving AZPs and non-AZPs, and evaluate them on Arabic, a language for which, as far as we know, there has been no prior work on joint resolution. Doing this also required creating a new version of the Arabic subset of the standard coreference resolution dataset used for the CoNLL-2012 shared task (Pradhan et al.,2012) in which both zeros and non-zeros are included in a single dataset.