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

TL;DR

This paper introduces an adversarial multitask learning approach to improve morphological tagging across dialects, especially benefiting low-resource dialects by learning dialect-invariant features.

Contribution

It proposes a novel combination of multitask learning and adversarial training for joint morphological modeling and cross-dialectal knowledge transfer.

Findings

Achieved state-of-the-art results for both dialects.

Adversarial training improves performance with smaller datasets.

Effective cross-dialectal morphological modeling.

Abstract

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.