awesome-hebrew-nlp [](https://github.com/sindresorhus/awesome)
January 13, 2023 ยท View on GitHub
Please feel free to create pull requests, or email Iddo Berger (iddoberger@gmail.com) to add links.
Links
https://data.gov.il/dataset/corpus - Morphologically tagged corpus
https://github.com/NLPH/NLPH - An initiative meant to bring Natural Language Processing capabilities in Hebrew to a level on par with international industry standards, keeping up with state-of-the-art techniques by providing open source implementations to new algorithms and tools, and making these capabilities publicly available for both public and commercial use.
https://github.com/omilab/Neural-Sentiment-Analyzer-for-Modern-Hebrew - Neural Sentiment Analyzer for Modern Hebrew
http://www.mila.cs.technion.ac.il/ - MILA - Technion's Knowledge Center for Processing Hebrew
https://hlp.nite.org.il/Default.aspx - Hebrew Language Project by the Israeli National Institute for Testing and Evaluation - Morphology dictionary, tagged corpora, language models, tokenizers and more (site in Hebrew)
https://github.com/habeanf/yap - Hebrew parser (Go)
https://github.com/synhershko/HebMorph - Hebrew stemmer (Java)
https://www.cs.bgu.ac.il/~yoavg/software/hebtokenizer/ - Hebrew tokenizer (Python). [Note from author: quite simplistic, but works.]
https://www.cs.bgu.ac.il/~nlpproj/ - Natural Language Processing Project - Ben-Gurion University
https://www.cs.bgu.ac.il/~yoavg/software/hebparsers/hebdepparser/ - Hebrew Dependency Parser (bundles a Hebrew pos-tagger and morphological segmenter as well). Parser is in Python+Cython, tagger in Java + Python-wrapper. [Note from parser's author: I am not maintaining the parser. For a newer, better supported dep parser, use YAP.]
https://www.cs.bgu.ac.il/~yoavg/software/hebparsers/hebconstparser/ - Hebrew Constituency Parser.
http://www.cs.technion.ac.il/~barhaim/MorphTagger/ - HMM based a part-of-speech tagger and word segmenter for Hebrew (Perl)
https://github.com/UniversalDependencies/UD_Hebrew - Hebrew Dependency Treebank
https://github.com/facebookresearch/fastText/blob/master/docs/pretrained-vectors.md - Pre-trained Hebrew word embeddings using Facebook's fastText
https://github.com/avichaychriqui/HeBERT - HeBERT: Pre-trained BERT for Polarity Analysis and Emotion Recognition
https://github.com/OnlpLab/AlephBERT/ - AlephBERT: a Pre-trained Language Model to Start Off your Hebrew NLP Application
License
To the extent possible under law, Iddo Berger has waived all copyright and related or neighboring rights to this work.