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 csrankings.org. 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!

news

Official announcement
"With the Natural Language Processing Program, ELLIS now counts 12 Fellow programs"
https://ellis.eu/news/ellis-launches-nlp-fellow-program

directed by Iryna Gurevych @iatitov @andre_t_martins 🎉

https://ellis.eu/programs/natural-language-processing

[1/2] Happy to share our #WMT2020 paper "Fast Interleaved Bidirectional Sequence Generation". We propose IBDecoder that accelerates decoding by ~2x-6x with almost no quality loss.

Paper: https://arxiv.org/abs/2010.14481
Code: https://github.com/bzhangGo/zero

w/ @iatitov and @RicoSennrich

[1/4] Analyzing Source and Target Contributions to NMT Predictions - new work with @iatitov and @RicoSennrich!

What influences the predictions in NMT: the source or the target prefix? We measure and find out!

Paper: https://arxiv.org/abs/2010.10907
Blog: https://lena-voita.github.io/posts/source_target_contributions_to_nmt.html #NLProc

[1/4] Excited to share our new work on improving end-to-end speech translation with adaptive feature selection, to appear at Findings of #emnlp2020.

Joint work with @iatitov, @bazril and @RicoSennrich.

Paper: https://arxiv.org/abs/2010.08518
Code: https://github.com/bzhangGo/zero

Load More...