0

D-Nikud: Enhancing Hebrew Diacritization with LSTM and Pretrained Models

A novel Hebrew diacritization method combining LSTM and BERT-based pre-trained models achieves state-of-the-art results on benchmark datasets, focusing on modern texts and gender-specific diacritization.

Year
2024
Venue
arXiv 2024
Authors
2
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2402.00075ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

D-Nikud, a novel approach to Hebrew diacritization that integrates the strengths of LSTM networks and BERT-based (transformer) pre-trained model. Inspired by the methodologies employed in Nakdimon, we integrate it with the TavBERT pre-trained model, our system incorporates advanced architectural choices and diverse training data. Our experiments showcase state-of-the-art results on several benchmark datasets, with a particular emphasis on modern texts and more specified diacritization like gender.

Authors

2