Data Augmentation Methods for Anaphoric Zero Pronouns

TL;DR

This paper introduces five data augmentation techniques to automatically generate and detect anaphoric zero pronouns in pro-drop languages, enhancing system performance.

Contribution

It presents novel data augmentation methods specifically designed for anaphoric zero pronouns and demonstrates their effectiveness in improving system accuracy.

Findings

Augmented data improves zero pronoun detection accuracy.

Enhanced systems outperform previous state-of-the-art results.

Methods are applicable to multiple pro-drop languages.

Abstract

In pro-drop language like Arabic, Chinese, Italian, Japanese, Spanish, and many others, unrealized (null) arguments in certain syntactic positions can refer to a previously introduced entity, and are thus called anaphoric zero pronouns. The existing resources for studying anaphoric zero pronoun interpretation are however still limited. In this paper, we use five data augmentation methods to generate and detect anaphoric zero pronouns automatically. We use the augmented data as additional training materials for two anaphoric zero pronoun systems for Arabic. Our experimental results show that data augmentation improves the performance of the two systems, surpassing the state-of-the-art results.