# Adversarial Multitask Learning for Joint Multi-Feature and Multi-Dialect Morphological Modeling

arXiv: https://arxiv.org/abs/1910.12702 · HTML: https://mlsanity.com/paper/1910.12702/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2019.

## Built on by (most cited first, 9 of 9)

- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Specializing Multilingual Language Models: An Empirical Study](https://mlsanity.com/paper/2106.09063/) (2021)
- [Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects](https://mlsanity.com/paper/2110.06852/) (2021)
- [Arabic Diacritics in the Wild: Exploiting Opportunities for Improved Diacritization](https://mlsanity.com/paper/2406.05760/) (2024)
- [Improving Arabic Diacritization by Learning to Diacritize and Translate](https://mlsanity.com/paper/2109.14150/) (2021)
- [Take the Hint: Improving Arabic Diacritization with Partially-Diacritized Text](https://mlsanity.com/paper/2306.03557/) (2023)
- [Transfer Learning in Conversational Analysis through Reusing Preprocessing Data as Supervisors](https://mlsanity.com/paper/2112.03032/) (2021)
- [Normalized Orthography for Tunisian Arabic](https://mlsanity.com/paper/2402.12940/) (2024)
- [Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models](https://mlsanity.com/paper/2603.16718/) (2026)

## Abstract (arXiv)

Morphological tagging is challenging for morphologically rich languages due to the large target space and the need for more training data to minimize model sparsity. Dialectal variants of morphologically rich languages suffer more as they tend to be more noisy and have less resources. In this paper we explore the use of multitask learning and adversarial training to address morphological richness and dialectal variations in the context of full morphological tagging. We use multitask learning for joint morphological modeling for the features within two dialects, and as a knowledge-transfer scheme for cross-dialectal modeling. We use adversarial training to learn dialect invariant features that can help the knowledge-transfer scheme from the high to low-resource variants. We work with two dialectal variants: Modern Standard Arabic (high-resource "dialect") and Egyptian Arabic (low-resource dialect) as a case study. Our models achieve state-of-the-art results for both. Furthermore, adversarial training provides more significant improvement when using smaller training datasets in particular.