Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks has been accepted at NeurIPS 2020. We’ve also released a blog post and released the code as part of the HuggingFace ecosystem. Check out a demo of RAG here
KILT: a Benchmark for Knowledge Intensive Language Tasks is now available on ArXiv! KILT is set of tools and data to accelerate research progress on open domain and knowledge intensive NLP, including open domain QA, fact checking, relation extraction and entity linking. KILT will make your work easier, more comparable and reproducible, and allow researchers to share components more easily.
check out the code, and leaderboard, and HuggingFace integrations.
Question and Answer Test-Train Overlap in Open-Domain Question Answering Datasets is now on ArXiv! Do you use NaturalQuestions, TriviaQA, or WebQuestions? It turns out 60% of test set answers are also in the train set. More surprising, 30% of test questions have a close paraphrase in the train set. We look at what this means for models. Annotations and code available here:
R4C: A Benchmark for Evaluating RC Systems to Get the Right Answer for the Right Reason was presented at ACL 2020. It previously won the “Best Linguistic Resource” award at the 26th annual meeting of the Japanese Association for Natural Language Processing.
“How Context Affects Language Models' Factual Predictions” has been been awarded Best Paper at AKBC 2020!
Pasquale’s paper Learning Reasoning Strategies in End-to-End Differentiable Proving will appear at ICML 2020! We propose a neuro-symbolic reasoning model that can learn to dynamically select and generate rules conditioned on the goal during their reasoning process via gradient-based optimisation.
UCL NLP members authored two chapters in Knowledge Graphs for eXplainable Artificial Intelligence: Foundations, Applications and Challenges, edited by IOS Press!
Senior Research Associate, Principal Investigator for H2020 CLARIFY
Visiting PhD Student
MRes Computational Statistics and Machine Learning
Now a senior lecturer at University of Cambridge
Now a PhD student at MIT
Now a research associate at University of Sheffield
Saku is a Ph.D. student at the University of Tokyo, interested in natural language understanding by machines.
Now a master student at Tohoku University
Now a Research Manager at Facebook
Now a post-doc at University of Ghent
Now a research scientist at Preferred Networks (PFN)
Now back to being a PhD student at Xerox Research Centre Europe
Now a Research Scientist at Facebook
Now an assistant professor at University of Copenhagen
Now an assistant professor at Tohoku University
Now a PhD student at University of Washington
V. Ivan Sanchez
Now an NLP researcher at Lenovo
Now back to being a PhD student at MIT
Now a student at Toyota Technological Institute at Chicago
Now a ML engineer at PolyAI
Cape is an open source large-scale open-domain Question Answering system.
stat-nlp-book is an interactive Statistical NLP book in Python, used for our StatNLP from 2016 onwards.
stat-nlp-book-scala is an interactive Statistical NLP book in Scala, used for our StatNLP course in 2015 / 16.
Jack the Reader is a Machine Reading framework for Question Answering, Natural Language Inference, and Link Prediction - see the paper here.
Neural Theorem Prover is an end-to-end differentiable logic reasoner, implementing the model described in End-to-end Differentiable Proving.
Inferbeddings is a link prediction framework that allows including First-Order background knowledge via adversarial training - the model is described in Adversarial Sets for Regularising Neural Link Predictors.
wolfe is a framework for building rich machine learning models, based on functional programming, factor graphs, optimization and composition.
ucleed is a biomedical event extractor that ranked first in several tracks of the BioNLP 2011 shared task.
thebeast is a Markov Logic inference and learning engine.
What’s Wrong With My NLP? is a visualizer for NLP problems.
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.