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.

news

From previous work: relations between mentions in document help to link entities to knowledge bases. @lephongxyz: we can do well without supervision, treating relations btw mentions as latent variables, #acl2018 poster, Tue 12.30-14.00 @EdinburghNLP @AmsterdamNlp

What does document-level NMT capture? Apparently, to a large degree, co-reference phenomena (and does this quite well). Interested: come to Lena Voita's talk at 11.20 on Tue (MT session). Joint work with @RicoSennrich @serdyukovp #acl2018 @EdinburghNLP @Yandex @AmsterdamNlp

4

Come see poster by @chunchuan_lyu on variational autoencoding for AMR parsing: VI with relaxed injective alignments, +3.4% F1 on the standard AMR semantic parsing benchmarks #acl2018 Monday, 12:30 - 14:00, https://t.co/5i1ChpQ278

Here are my slides from today at Edinburgh (@InfAtEd @EdinburghNLP) on #NLProc and group dynamics. Thanks @SICSA_Scotland for the visiting fellowship. https://t.co/AuwzCAd6am

"I feel a mastery of my own tools in a way that I was never motivated to gain before this." -- @nsaphra on the unexpected benefits of coding-by-voice: https://t.co/UXRV5yr6pY by @AnnaNowo

Load More...