The Natural Language Processing Group at the University of Edinburgh (EdinburghNLP) is a group of faculty, postdocs, and PhD students working on algorithms that make it possible for computers to understand and produce human language. We do research in all core areas of natural language processing, including morphology, parsing, semantics, discourse, language generation, and machine translation. EdinburghNLP also has a strong track record of work at the interface of NLP with other areas, including speech technology, machine learning, computer vision, cognitive modeling, social media, information retrieval, robotics, bioinformatics, and educational technology.

With 11 core faculty members, EdinburghNLP is one of the largest NLP group in the world. It is also ranked as the most productive group in the area, according to Our achievements include the award-winning neural machine translation system Nematus and the high-performance language modeling toolkit KenLM. EdinbughNLP faculty have a strong record of getting high-profile grants, and have so far won a total of five European Research Council (ERC) grants.

We are looking for new PhD students! Join us. Also, please check out the new UKRI Centre for Doctoral Training in Natural Language Processing!


[1/3] Information-Theoretic Probing with Minimum Description Length: a new paper with @iatitov, and a blog post!

We propose an alternative to the standard probes, which is more informative, stable, and sensible.


🎉The wait is over! #WeNeedToTalkAboutAI is back!🎉

The next public discussion co-hosted by @Ed_intelligence and @UoE_EFI will take place Mon 16 March, where the panel will examine ethical issues that arise from using assistive products. See you there!

The Potterrow Development, including the @BayesCentre recently won a Civic Trust Award. Congratulations to everyone involved in the project.


Our paper "The Effect of User Psychology on the Content of Social Media Posts: Originality and Transitions Matter" got accepted to @FrontPsychol.

Authors: @LushiChenLucia, @Walid_Magdy, @mariawolters

An excellent example of using #DataScience in the field of #Psychology

New release of the monolingual news crawl for #wmt20. This contains 60G of compressed shuffled news text, spanning 12 years and 40 languages.

Load More...