I am an assistant professor in the Center for Social Data Science at the University of Copenhagen (). I am currently also a visiting researcher with the RIKEN Center for Computational Science (Japan). My main research area is Natural Language Processing, in particular model analysis and evaluation of natural language understanding systems.

Before moving to Denmark, I was a postdoctoral research associate in the University of Massachusetts, working with Anna Rumshisky on sentiment analysis, question answering and analysis of meaning representations. I hold a Ph.D. degree from the Department of Language and Information Sciences at the University of Tokyo (Japan).

News

14.07.2022 I'm giving an invited talk at the First Workshop on Adversarial Data Collection (NAACL 2022).

17.06.2022 I'm giving a keynote at CLIN 2022.

06.06.2022 Absolutely thrilled to be part of the Efficient and Equitable Natural Language Processing in the Age of Deep Learning.

25.05.2022 The third edition of Workshop on Insights from Negative Results NLP is happening in hybrid mode at ACL 2022.

29.04.2022 An invited talk in the University of Edinburgh on .

07.04.2022 "Data Governance in the Age of Large-Scale Data-Driven Language Technology" (a collaboration with HuggingFace's BigScience project) is accepted to FaccT 2022! Preprint

07.04.2022 A paper on the challenges of paper-reviewer assignment was accepted for NAACL 2022 main track! Preprint coming soon.

31.03.2022 An invited talk at Stanford NLP seminar!

14.03.2022 Our QA Dataset Explosion will appear in ACM CSUR!

14.02.2022 An invited talk at Oslo Language Technology Group, presenting a collection of findings on generalization in Transformer-based models.

07.02.2022 SODAS is open to hosting interdisciplinary PhD projects broadly concerning AI and society - co-supervised by me and real social scientists! See the call for DDSA fellowships (deadline: March 20).

15.01.2022 I'm one of the Senior Area Chairs for Model Analysis and Interpretability track at ACL 2022.

15.12.2021 An invited talk at London ML Meetup, presenting a collection of BERTology thoughts and findings.

7-12.11.2021 I am one of the recipients of the Widening NLP award, which allows me to travel to EMNLP 2021. I will speak at the panel "The Peer Review Process and Widening NLP", and present two papers: "Just What Do You Think You're Doing, Dave?" (EMNLP Findigns, presented at Natural Legal Language Processing Workshop), and "Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics" (Workshop on Insights from Negative Results)

09.11.2021 "Changing the world by changing the data": invited talk at the Data-centric AI day at France in AI.

27.10.2021 Presenting a collection of BERTology findings for the Technical University of Denmark.

04.10.2021 Our paper Generalization in NLI: Ways (Not) To Go Beyond Simple Heuristics is accepted to Workshop on Insights from Negative Results in NLP.

21.09.2021 An invited talk at Toronto ML Summit on the real-world effects of the data we use in NLP.

31.08.2021 New blog post: BERT Busters: Outlier Dimensions that Disrupt Transformers.

25.08.2021 New paper in EMNLP Findings 2021: 'Just What do You Think You're Doing, Dave?' A Checklist for Responsible Data Use in NLP

14.08.2021 Interview on peer review for Science Report

03.08.2021 Virtual talk at ACL2021: Changing the world by changing the data

28.07.2021 BigScience Episode 1 is happening! Thrilled to collaborate with the data governance group co-led by Margaret Mitchell.

27.07.2021 New preprint with Matt Gardner and Isabelle Augenstein: QA Dataset Explosion

30.06.2021My first podcast interview! Talking to the Gradient Podcast about peer review.

17.06.2021 Virtual talk at L3-AI conference (Rasa): A primer in BERTology: what we know about how BERT works.

07.05.2021 Virtual talk at LTI colloquium (Carnegie Mellon University): The quest for difficult benchmarks in question answering and reading comprehension.

05.05.2021 :tada: One long paper accepted to ACL 2021 main track, and two to Findings! Preprints coming.

20.04.2021 Tutorial on Reviewing NLP research at EACL 2021.

12.01.2021 The Primer in BERTology came out in TACL, and will be presented at NAACL 2021.

02.12.2020 What Can We Do To Improve Peer Review in NLP is featured in the Science Report (and also the Gradient).

30.10.2020 I am the new secretary of SIGREP! Many thanks to all who voted for me.

25.10.2020 Two papers accepted! When BERT plays the lottery, all tickets are winning will appear in EMNLP 2020, and What Can We Do To Improve Peer Review in NLP - in Findings of EMNLP.

17.09.2020 Virtual talk at NYU Center for Data Science: When BERT plays the lottery, all tickets are winning.

25.06.2020 Our Primer in BERTology is accepted to TACL!

18.06.2020 How Much Should Conversational AI Developers know about ML and Linguistics? I'm in a panel discussion with Emily M. Bender, Thomas Wolf, and Vladimir Vlasov at the Level 3 AI Assistant Conference.

01.06.2020 Starting my new job at the Center for Social Data Science in the University of Copenhagen!

04.2020 Honored to serve as publicity chair for both EMNLP and COLING 2020!