CLAILGNov 3, 2022

Transformers on Multilingual Clause-Level Morphology

arXiv:2211.01736v2291 citationsh-index: 27
AI Analysis

This work addresses morphological processing for multiple languages, but it is incremental as it applies existing methods to a new shared task.

The authors tackled multilingual clause-level morphology tasks (inflection, reinflection, and analysis) by exploring transformers with data augmentation and prefix-tuning, achieving first place in all three tasks at the MRL 2022 shared task.

This paper describes our winning systems in MRL: The 1st Shared Task on Multilingual Clause-level Morphology (EMNLP 2022 Workshop) designed by KUIS AI NLP team. We present our work for all three parts of the shared task: inflection, reinflection, and analysis. We mainly explore transformers with two approaches: (i) training models from scratch in combination with data augmentation, and (ii) transfer learning with prefix-tuning at multilingual morphological tasks. Data augmentation significantly improves performance for most languages in the inflection and reinflection tasks. On the other hand, Prefix-tuning on a pre-trained mGPT model helps us to adapt analysis tasks in low-data and multilingual settings. While transformer architectures with data augmentation achieved the most promising results for inflection and reinflection tasks, prefix-tuning on mGPT received the highest results for the analysis task. Our systems received 1st place in all three tasks in MRL 2022.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes