News

News Archive →

People

Sebastian Riedel

Sebastian Riedel

Professor

Sebastian Riedel

Sebastian works in NLP and Machine Learning. He is particularly interested in helping machines to read more accurately by leveraging...

Pontus Stenetorp

Pontus Stenetorp

Lecturer

Pontus Stenetorp

Pontus works somewhere in the intersection between Natural Language Processing and Machine Learning. He is particularly interested in...

Tim Rocktäschel

Tim Rocktäschel

Affiliated Faculty (Lecturer)

Tim Rocktäschel

Reinforcement Learning – Deep Learning – Natural Language Processing

Tim’s work focuses on developing agents that are...

Ed Grefenstette

Ed Grefenstette

Honorary Reader

Ed Grefenstette

Ed is interesting in teaching machines to understand and communicate using language (formal and natural), and in both neural and symbolic...

Pasquale Minervini

Pasquale Minervini

Senior Research Fellow, Principal Investigator for H2020 CLARIFY

Pasquale Minervini

Pasquale is interested in Machine Learning and Reasoning. He is the Principal Investigator of the CLARIFY H2020 project on the UCL end.

Linqing Liu

Linqing Liu

PhD Student

Linqing Liu

Linqing is a first year PhD student with broad interests in NLP and Machine Learning. She is currently working on question answering.

Matko Bošnjak

Matko Bošnjak

PhD Student

Matko Bošnjak

Matko’s interests include both natural and unnatural language processing, and their interplay. Specifically, he’s enjoying...

Max Bartolo

Max Bartolo

PhD Student

Max Bartolo

Max’s current research focuses on natural language processing, with particular interest in question answering and machine reasoning.

Maximilian Mozes

Maximilian Mozes

PhD Student

Maximilian Mozes

Maximilian’s research focuses on the intersection of adversarial machine learning and natural language processing.

Mikayel Samvelyan

Mikayel Samvelyan

PhD Student

Mikayel Samvelyan

Mikayel’s interests lie in reinforcement learning, natural language processing and multi-agent systems.

Minqi Jiang

Minqi Jiang

PhD student

Minqi Jiang

Minqi studies how decision-making agents can make use of compositional structures, like language, to learn more generalizable behaviors.

Patrick Lewis

Patrick Lewis

PhD Student

Patrick Lewis

Patrick is a first year PhD student, interested in Transfer Learning, Machine Reading and leveraging world knowledge to improve predictions...

Tom Crossland

Tom Crossland

PhD Student

Tom Crossland

Tom is an astrophysicist working with the MR group and the Mullard Space Science Laboratory, interested in Machine Learning applications to...

Yao Lu

Yao Lu

PhD Student

Yao Lu

Yao is interested in everything.

Yihong Chen

Yihong Chen

PhD Student

Yihong Chen

Yihong is interested in almost everything, currently working on methods that empower efficient learning of symbols. Welcome any messages...

Yuxiang Wu

Yuxiang Wu

PhD Student

Yuxiang Wu

Yuxiang is a third-year PhD student, interested in Question Answering, Knowledge Base, and other knowledge related tasks.

Zhengyao Jiang

Zhengyao Jiang

PhD Student

Zhengyao Jiang

Zhengyao is interested in topics about reinforcement leanring, relational inductive bias, and bridging symbolic reasoning and deep learning....

Alastair Roberts

Alastair Roberts

Visiting Researcher

Alastair Roberts

Alastair’s interests lie in natural language processing & machine learning. His current work is focused on question answering.

Alumni

Andreas Vlachos

Andreas Vlachos

Now a senior lecturer at University of Cambridge

Andreas Vlachos

Former Research Associate

Johannes Welbl

Johannes Welbl

Now a Research Scientist at DeepMind

Johannes Welbl

Former PhD Student

Luke Hewitt

Luke Hewitt

Now a PhD student at MIT

Luke Hewitt

Former Intern

Gerasimos Lampouras

Gerasimos Lampouras

Now a research associate at University of Sheffield

Gerasimos Lampouras

Former Research Associate

Saku Sugawara

Saku Sugawara

Now back to being a Ph.D. student at the University of Tokyo.

Saku Sugawara

Former Visiting PhD Student

Sonse Shimaoka

Sonse Shimaoka

Now a master student at Tohoku University

Sonse Shimaoka

Former Intern

Zhao Zhang

Zhao Zhang

Now back to being a PhD student at the Chinese Academy of Sciences.

Zhao Zhang

Former Visiting PhD Student

Guillaume Bouchard

Guillaume Bouchard

Now a Research Manager at Facebook

Guillaume Bouchard

Former Senior Research Associate

Thomas Demeester

Thomas Demeester

Now a post-doc at University of Ghent

Thomas Demeester

Former Visiting Researcher

Jason Naradowsky

Jason Naradowsky

Now a research scientist at Preferred Networks (PFN)

Jason Naradowsky

Former Research Associate

Théo Trouillon

Théo Trouillon

Now back to being a PhD student at Xerox Research Centre Europe

Théo Trouillon

Former Visiting PhD Student

Marzieh Saeidi

Marzieh Saeidi

Now a Research Scientist at Facebook

Marzieh Saeidi

Former Research Scientist at Facebook

Isabelle Augenstein

Isabelle Augenstein

Now an associate professor at University of Copenhagen

Isabelle Augenstein

Former Research Associate

Naoya Inoue

Naoya Inoue

Now an assistant professor at Tohoku University

Naoya Inoue

Former Visiting Researcher

Tim Dettmers

Tim Dettmers

Now a PhD student at University of Washington

Tim Dettmers

Former Intern

V. Ivan Sanchez

V. Ivan Sanchez

Now an NLP researcher at Lenovo

V. Ivan Sanchez

Former PhD Student

Andres Campero

Andres Campero

Now back to being a PhD student at MIT

Andres Campero

Former Visiting PhD Student

Takuma Yoneda

Takuma Yoneda

Now a student at Toyota Technological Institute at Chicago

Takuma Yoneda

Former Intern

Georgios Spithourakis

Georgios Spithourakis

Now a ML engineer at PolyAI

Georgios Spithourakis

Former PhD Student

Publications

In EMNLP, 2020.

In TACL, 2020.

ArXiv 2020.

ArXiv 2020.

In ACL 2020.

ArXiv 2020.

Datasets

In this work we investigate this annotation methodology and apply it in three different settings, collecting a total of 36,000 samples with progressively stronger models in the annotation loop. This allows us to explore questions such as the reproducibility of the adversarial effect, transfer from data collected with varying model-in-the-loop strengths, and generalisation to data collected without a model. We find that training on adversarially collected samples leads to strong generalisation to non-adversarially collected datasets, yet with progressive performance deterioration with increasingly stronger models-in-the-loop. Furthermore, we find that stronger models can still learn from datasets collected with substantially weaker models-in-the-loop. When trained on data collected with a BiDAF model in the loop, RoBERTa achieves 39.9F1 on questions that it cannot answer when trained on SQuAD - only marginally lower than when trained on data collected using RoBERTa itself (41.0F1).

KILT is a resource for training, evaluating and analyzing NLP models on Knowledge Intensive Language Tasks. KILT has been built from 11 datasets representing 5 tasks. All these datasets have been grounded in a single pre-processed wikipedia dump, allowing for fairer and more consistent evaluation and enabling new task setups such as multitask and transfer learning with minimal effort. KILT also provides tools to analyze and understand the predictions made by models, as well as the evidence they provide for their predictions.

A multi-way aligned extractive QA evaluation benchmark MLQA contains QA instances in 7 languages, English, Arabic, German, Spanish, Hindi, Vietnamese and Simplified Chinese.

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.

Multi-hop question answering datasets from two different domains, designed to enabe models to combine disjoint pieces of textual evidence.