Multilingual Sequence-to-Sequence Models for Hebrew NLP

Matan Eyal, Hila Noga, Roee Aharoni, Idan Szpektor, Reut Tsarfaty

Abstract
Recent work attributes progress in NLP to large language models (LMs) with increased model size and large quantities of pretraining data. Despite this, current state-of-the-art LMs for Hebrew are both under-parameterized and under-trained compared to LMs in other languages. Additionally, previous work on pretrained Hebrew LMs focused on encoder-only models. While the encoder-only architecture is beneficial for classification tasks, it does not cater well for sub-word prediction tasks, such as Named Entity Recognition, when considering the morphologically rich nature of Hebrew. In this paper we argue that sequence-to-sequence generative architectures are more suitable for large LMs in morphologically rich languages (MRLs) such as Hebrew. We demonstrate this by casting tasks in the Hebrew NLP pipeline as text-to-text tasks, for which we can leverage powerful multilingual, pretrained sequence-to-sequence models as mT5, eliminating the need for a separate, specialized, morpheme-based, decoder. Using this approach, our experiments show substantial improvements over previously published results on all existing Hebrew NLP benchmarks. These results suggest that multilingual sequence-to-sequence models present a promising building block for NLP for MRLs.
Anthology ID:
2023.findings-acl.487
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7700–7708
Language:
URL:
https://aclanthology.org/2023.findings-acl.487
DOI:
10.18653/v1/2023.findings-acl.487
Bibkey:
Cite (ACL):
Matan Eyal, Hila Noga, Roee Aharoni, Idan Szpektor, and Reut Tsarfaty. 2023. Multilingual Sequence-to-Sequence Models for Hebrew NLP. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7700–7708, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Multilingual Sequence-to-Sequence Models for Hebrew NLP (Eyal et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.findings-acl.487.pdf
PDF Search