AlephBERT:A Hebrew Large Pre-Trained Language Model to Start-off your Hebrew NLP Application With

TL;DR

Hebrew NLP has lagged due to morphology complexity and limited resources. The authors introduce AlephBERT, a large Hebrew PLM with a 52K vocabulary trained on Oscar, Twitter, and Hebrew Wikipedia, evaluated in two sizes across a full Hebrew NLP pipeline. They demonstrate state-of-the-art results on segmentation, POS, full morphological tagging, NER, and sentiment across multiple Hebrew benchmarks, and provide public release and a demo to facilitate further Hebrew NLP development. This work closes a significant resource gap for Hebrew and provides a practical starting point for downstream Hebrew applications and research.

Abstract

Large Pre-trained Language Models (PLMs) have become ubiquitous in the development of language understanding technology and lie at the heart of many artificial intelligence advances. While advances reported for English using PLMs are unprecedented, reported advances using PLMs in Hebrew are few and far between. The problem is twofold. First, Hebrew resources available for training NLP models are not at the same order of magnitude as their English counterparts. Second, there are no accepted tasks and benchmarks to evaluate the progress of Hebrew PLMs on. In this work we aim to remedy both aspects. First, we present AlephBERT, a large pre-trained language model for Modern Hebrew, which is trained on larger vocabulary and a larger dataset than any Hebrew PLM before. Second, using AlephBERT we present new state-of-the-art results on multiple Hebrew tasks and benchmarks, including: Segmentation, Part-of-Speech Tagging, full Morphological Tagging, Named-Entity Recognition and Sentiment Analysis. We make our AlephBERT model publicly available, providing a single point of entry for the development of Hebrew NLP applications.