• YAP Demo

    online demo is available here

Why ONLP?

Multidisciplinarity

Our team members come from diverse background as Commuter science, theoretical linguistics, computational linguistics, Data science, Software engineers, and more

Multilinguality

We work English, Hebrew, and many other languages, and we take active part in the development of universal parsing resources such as UD (universal dependencies). Currently, we are the only research lab actively developing Infrastructure for Hebrew NLP.

Check out our Hebrew Parser

Diversity

Our research team is completely balanced in terms of gender! with male and female researchers at all levels. We come from diverse backgrounds and ages. We care that everyone feels safe and comfortable! Our creative sparks come precisely through that.

Team

Everyone say 'Hi' :-)


PI: Dr. Reut Tsarfaty

Head of the ONLP lab. Interested in natural language programming, morphological, syntactic and semantic parsing. Recipient of ERC-StG Grant #677352 and an ISF grant #1739/26

Dr. Royi Lachmi

Postdoc

Dr. Victoria Basmova

Postdoc.

Lab CTO: Amit Seker

MSc Student.

Shoval Sadde

Linguist.

Dan Bareket

Data Scientist.

Tzuf Argaman

PhD Candidate at Ber-Ilan University. Researching grounded and executable semantic parsing, zero-shot learning and multimodality.

Yochai Gurman

MSc student, looking into cause-effect reasoning and argumentation by day,
secretly interested in computational humor by night

Stav Klein

Linguist, unblackboxing RNNs, semantic parsing of Hebrew with CCG, morphological tagger in Hebrew

Projects

Here is a taste of the projects we are currently working on.


Natural language programming: Turning Text into Executable Code

Funded by an ERC-Starting grant #677352

2016 - 2022

In this project we view the programming task as automatically generating a system based on a verbal description of its behavior. Our task is to semantically parse natural language requirements into a formal executable system, using advanced statistical and deep learning methods

Automatic Broad-Coverage Cross-Linguistic Semantic Parsing

Funded by an ISF research grant #1739/26

2016 - 2020

In this project we use deep learning methods for acquiring broad coverage semantic representations that can accommodate morphological, morphosyntactic and morphosemantic phenomena in the same computational framework

Infrastructure for Hebrew Natural Language Processing


Constantly Ongoing

We develop state-of-the-art open-source Hebrew NLP resources and algorithms, including but not limited to Hebrew morphological and syntactic analysis, sentiment analysis, named-entity recognition and more

Check out our demo

Publications

Peer-reviewed articles


Paz-Argrman, Tzuf; Tsarfaty, Reut RUN through the Streets: A New Dataset and Baseline Models for Realistic Urban Navigation. EMNLP 2019

Tsarfaty, Reut; Seker, Amit; Sadde, Shoval; Klein, Stav. What's Wrong with Hebrew NLP? And How to Make it Right. EMNLP 2019 Demo Paper

More, Amir; Seker, Amit; Basmova, Victoria; Tsarfaty, Reut. Joint Transition-Based Models for Morpho-Syntactic Parsing: Parsing Strategies for MRLs and a Case Study from Modern Hebrew. Transactions of the Association for Computational Linguistics 7. Pages 33-48, 2019. MIT Press One Rogers Street, Cambridge, MA 02142-1209 USA

Sadde, Shoval; Seker, Amit; Tsarfaty, Reut. The Hebrew Universal Dependency Treebank: Past Present and Future. In Proceedings of the Second Workshop on Universal Dependencies (UDW 2018). Pages 133-143, 2018

Seker, Amit; More, Amir; Tsarfaty, Reut. Universal Morpho-syntactic Parsing and the Contribution of Lexica: Analyzing the ONLP Lab Submission to the CoNLL 2018 Shared Task. In Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Pages 208-215, 2018

Amram, Adam; Ben-David, Anat; Tsarfaty, Reut. Representations and Architectures in Neural Sentiment Analysis for Morphologically Rich Languages: A Case Study from Modern Hebrew. In Proceedings of the 27th International Conference on Computational Linguistics. Pages 2242-2252, 2018

More, Amir; Çetinoğlu, Özlem; Çöltekin, Çağrı; Habash, Nizar; Sagot, Benoît; Seddah, Djamé; Taji, Dima; Tsarfaty, Reut. CoNLL-UL: Universal morphological lattices for Universal Dependency parsing. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC), 2018

Tsarfaty, Reut. The Natural Language Programming (NLPRO) Project: Turning Text into Executable Code. In Proceedings of the REFSQ Workshops, 2018

More, Amir; Tsarfaty, Reut. Universal Joint Morph-Syntactic Processing: The Open University of Israel’s Submission to The CoNLL 2017 Shared Task. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. Pages 253-264, 2017

Cagan, Tomer; Frank, Stefan L; Tsarfaty, Reut. Data-driven broad-coverage grammars for opinionated natural language generation (ONLG). In Proceedings of the International Meeting of the Association for Computational Linguistics, 2017

More, Amir; Tsarfaty, Reut. Data-driven morphological analysis and disambiguation for morphologically rich languages and universal dependencies. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics. Pages 337-348, 2016

Nivre, Joakim; De Marneffe, Marie-Catherine; Ginter, Filip; Goldberg, Yoav; Hajic, Jan; Manning, Christopher D; McDonald, Ryan T; Petrov, Slav; Pyysalo, Sampo; Silveira, Natalia; Tsarfaty, Reut; Zeman, Dan. Universal Dependencies v1: A Multilingual Treebank Collection. In Proceedings of LREC. 2016

Tsarfaty, Reut; Pogrebezky, Ilia; Weiss, Guy; Natan, Yaarit; Szekely, Smadar; Harel, David. Semantic parsing using content and context: A case study from requirements elicitation. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Pages 1296-1307, 2014

Seddah, Djamé; Kübler, Sandra; Tsarfaty, Reut. Introducing the SPMRL 2014 shared task on parsing morphologically-rich languages. In Proceedings of the First Joint Workshop on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical Languages. Pages 103-109, 2014

Cagan, Tomer; Frank, Stefan L; Tsarfaty, Reut. Generating subjective responses to opinionated articles in social media: an agenda-driven architecture and a turing-like test. In Proceedings of the Joint Workshop on Social Dynamics and Personal Attributes in Social Media, pages 58-67, 2014

Tsarfaty, Reut. Syntax and Parsing of Semitic Languages. Natural Language Processing of Semitic Languages, 67-128, 2014, Springer, Berlin, Heidelber

Stay in touch with us

Interested in hearing more? Drop us a note


Bar-Ilan University, bldg. 216
Room 002

reut.tsarfaty@gmail.com