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!


#acl2019nlp paper by Lena Voita "Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned" tl;dr analysis and (L0) pruning of the Transformer
with @RicoSennrich, David Talbot, Fedor Moiseev


EMNLP reviewers: if you are reviewing a paper similar to one you reviewed in ACL, don't assume the paper hasn't changed! Look carefully at the new version to not automatically repeat your previous review which might be no longer relevant. #nlproc #emnlp19

Our ACL paper "Interpretable Neural Predictions with Differentiable Binary Variables" is now online! TLDR sparse reparameterized samples 🤹‍♂️+ unbiased gradients 🎯= effective latent rationales 🖍for text classification 📄. With @wilkeraziz and @iatitov

Sharing soon: Interpretable Neural Predictions with Differentiable Binary Variables (ACL) with @joostbastings @iatitov, Latent Variable Model for Multi-modal Translation (ACL) with @CalixtoIacer @mriosb08; and Block Neural Autoregressive Flow (UAI) with @nicola_decao @iatitov

Thrilled to have four papers accepted at @ACL2019_Italy! Congratulations to Elena Voita, Biao Zhang, and collaborators (@iatitov, David Talbot, Fedor Moiseev)! #ACL2019NLP

Load More...