
Academic lab · Edinburgh, United Kingdom
EdinburghNLP
EdinburghNLP is the University of Edinburgh's natural language processing group, ranked among the most productive in the world and the home of Nematus.
Edinburgh, United Kingdom
- Type
- Academic lab
- Based in
- Edinburgh, United Kingdom
- Key papers
- 2
- Featured projects
- 7
About
EdinburghNLP brings together faculty, postdocs and PhD students in the School of Informatics. Its research covers language modelling, morphology, parsing, semantics, discourse, generation and machine translation, with links to speech, vision and robotics.
The group reports a faculty of more than a dozen core members and five European Research Council grants, and it is ranked first for NLP output by csrankings.org. It publishes code and data openly, including the Nematus neural machine translation toolkit, the XSum summarization dataset and a widely used list of hallucination-detection papers.
Mission and ambitionsTo develop algorithms that let computers understand and produce human language, and to share the resulting tools with the research community.
Known for
- 01
Nematus neural machine translation toolkit
- 02
XSum extreme summarization dataset
- 03
Leading academic NLP faculty
Milestones
- 2016
Nematus repository created
The open-source neural machine translation system was first published on GitHub.
- 2017
Nematus toolkit paper
Sennrich, Firat, Cho, Birch, Haddow and colleagues described the toolkit on arXiv.
- 2018
XSum dataset
Narayan, Cohen and Lapata introduced topic-aware convolutional networks and the extreme summarization dataset.
- 2023
Awesome hallucination detection list
The group opened a curated list of papers on hallucination detection that became its most starred repository.
- 2025
MMLongBench
A benchmark for long-context vision-language models was released by the group.
Open source
List of papers on hallucination detection in LLMs. (1,141 stars)
Open-Source Neural Machine Translation in Tensorflow (805 stars)
Topic-Aware Convolutional Neural Networks for Extreme Summarization (378 stars)
Ranking Sentences for Extractive Summarization with Reinforcement Learning (275 stars)
Model with 1 likes on the Hub.
Model with 0 likes on the Hub.
- EdinburghNLP/xsumdataset
Dataset with 157 likes on the Hub.
Research papers
Notable releases
Openness
Code and datasets are public on GitHub and Hugging Face.
People
- Mirella LapataProfessor of natural language processing
- Pasquale MinerviniFaculty member
- Edoardo PontiFaculty member
- Beatrice AlexFaculty member
- Sharon GoldwaterFaculty member
- Jeff DaltonFaculty member
Listed from the lab's own pages and public profiles.
Contact and community
Contact through the group website.
Sources
Compiled from the lab's public pages, Hugging Face and GitHub. Last checked 2026-11-17. Something wrong or out of date? Tell us on Discord.



