News
- 10/07/2023:
Our paper, What the DAAM: Interpreting Stable Diffusion Using Cross Attention, has won a Best Paper Award at ACL 2023! Congrats to authors Linqing and Pontus!
- 21/09/2022:
Yihong will be presenting ReFactorGNNs in ELLIS PhD Symposium 2022. Come to our poster if you are curious about why factorisation-based models are special message-passing GNNs!
- 15/09/2022:
Our paper ReFactorGNNs: Revisiting Factorisation-based Models from a Message-Passing Perspective has been accepted by NeurIPS 2022! Congrats Yihong, Pushkar, Luca, Pasquale, Pontus and Sebastian!
- 18/05/2022:
Our work Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity has been selected as an outstanding paper at ACL 2022!
- 26/03/2022:
The call for participation for the Shared Task at the DADC Workshop co-located with NAACL ‘22 in Seattle is now live! We have three fantastic tracks for you to participate in. Sign up here!
- 19/03/2022:
Additional resources from our work on Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation at EMNLP 2021 are now available! We are releasing a collection of synthetically-generated adversarial QA pairs and related resources as well as the models used to generate the questions.
- 28/02/2022:
Our AAAI 2022 tutorial, On Explainable AI: From Theory to Motivation, Industrial Applications, XAI Coding & Engineering Practices, was an outstanding success, with more than 600 attendees – check it out! Congratulations Pasquale and collaborators!
People
Pontus Stenetorp
Professor
Sebastian Riedel
Honorary Professor
David Adelani
Senior Research Fellow
Oana-Maria Camburu
Senior Research Fellow
Xuanli He
Research Fellow
Eduardo Sánchez
PhD Student
Jiayi Wang
PhD Student
Karen Hambardzumyan
PhD Student
Linqing Liu
PhD Student
Lovish Madaan
PhD Student
Sohee Yang
PhD student
Wiem Ben Rim
PhD Student
Yao Lu
PhD Student
Yihong Chen
PhD Student
Yuxiang Wu
PhD Student
Alice Winters
Group Administrator
Alumni
Max Bartolo
Now a Modelling Lead at Cohere
Pasquale Minervini
Now an Associate Professor at Edinburgh University
Luca Franceschi
Now a Research Scientist at Amazon
Tim Rocktäschel
Now a Postdoc at Oxford University
Maximilian Mozes
Now a Member of Technical Staff at Cohere
Patrick Lewis
Now a Research Scientist at FAIR
Tom Crossland
Now a a Teaching Fellow at Imperial College London
Matko Bošnjak
Now a Research Scientist at DeepMind
Alastair Roberts
Alastair’s interests lie in natural language processing & machine learning.
Johannes Welbl
Now a Research Scientist at DeepMind
Luke Hewitt
Now a PhD student at MIT
Gerasimos Lampouras
Now a research associate at University of Sheffield
Saku Sugawara
Now back to being a Ph.D. student at the University of Tokyo.
Sonse Shimaoka
Now a master student at Tohoku University
Zhao Zhang
Now back to being a PhD student at the Chinese Academy of Sciences.
Andreas Vlachos
Now a senior lecturer at University of Cambridge
Guillaume Bouchard
Now CEO at CheckStep
Thomas Demeester
Now a post-doc at University of Ghent
Jason Naradowsky
Now a research scientist at Preferred Networks (PFN)
Théo Trouillon
Now back to being a PhD student at Xerox Research Centre Europe
Marzieh Saeidi
Now a Research Scientist at Facebook
Isabelle Augenstein
Now an associate professor at University of Copenhagen
Naoya Inoue
Now an assistant professor at Tohoku University
Tim Dettmers
Now a PhD student at University of Washington
V. Ivan Sanchez
Now an NLP researcher at Lenovo
Andres Campero
Now back to being a PhD student at MIT
Takuma Yoneda
Now a student at Toyota Technological Institute at Chicago
Georgios Spithourakis
Now a ML engineer at PolyAI
Publications
Datasets
SynQA
A synthetic dataset of 315k QA pairs on passages from SQuAD designed to help make QA models more robust to human adversaries. This resource is also available in HuggingFace datasets at https://huggingface.co/datasets/mbartolo/synQA.
AdversarialQA (from Beat the AI)
A dataset of 36k challenging extractive QA pairs consisting of training, evaluation and test data collected using three different models-in-the-loop: BiDAF, BERT and RoBERTa.
KILT: a Benchmark for Knowledge Intensive Language Tasks
A resource for training, evaluating and analyzing NLP models on Knowledge Intensive Language Tasks. KILT has been built from 11 datasets representing 5 tasks.
MLQA
A multi-way aligned extractive QA evaluation benchmark MLQA contains QA instances in 7 languages, English, Arabic, German, Spanish, Hindi, Vietnamese and Simplified Chinese.
ShARC: Shaping Answers with Rules through Conversation
A collection of 32k task instances based on real-world rules and crowd-generated questions and scenarios requiring both the interpretation of rules and the application of background knowledge.
WikiHop & MedHop (QAngaroo)
Multi-hop question answering datasets from two different domains, designed to enabe models to combine disjoint pieces of textual evidence.