Joint Coreference Resolution for Zeros and non-Zeros in Arabic
This work addresses coreference resolution for Arabic, a language lacking prior joint models, by integrating zero and non-zero mention resolution, though it is incremental as it adapts existing joint approaches to a new language.
The paper tackles the problem of jointly resolving anaphoric zero pronouns and full mentions in Arabic, which were previously treated as separate tasks, by introducing two joint architectures and creating a new annotated dataset for evaluation, achieving results that demonstrate the feasibility of joint modeling in Arabic.
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.