Maartje ter Hoeve

About

I am a PhD candidate at the University of Amsterdam, supervised by Prof. Maarten de Rijke and Dr. Julia Kiseleva.

Having a background in Artificial Intelligence and Linguistics, my main research focus is on Natural Language Processing and Understanding. I am especially interested in how we can learn from humans and their cognition to improve our AI systems.

In September 2017 I obtained my master's degree in Artificial Intelligence from the University of Amsterdam. I did my bachelor's degree in Linguistics, at the University of Amsterdam and partially at the University of Edinburgh.

You can find my CV here.

News

05/2023: I defended my PhD thesis, called 'New Directions in Human-Centered Language Technology. Understanding and Improving NLP Models' at the University of Amsterdam! You can find my thesis here.

05/2022: The IGLU challenge has been accepted at NeurIPS again! Looking forward to this second edition, more info soon!

04/2022: I started an internship at Apple Machine Learning Research in Paris! I will work with Natalie Schluter.

04/2022: Our paper "What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization Research" has been accepted to NAACL 2022! You can read the paper here!

03/2022: I will present our paper "Towards Interactive Language Modeling" at the SPA-NLP workshop at ACL! Paper available here!

01/2022: Our paper "CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks" has been accepted at AISTATS 2022! Read the paper here!

12/2021: During my internship at FAIR I worked on Interactive Language Modeling, together with Evgeny Kharitonov, Dieuwke Hupkes and Emmanuel Dupoux. The preprint of the work is now available here!

12/2021: We will present our IGLU competition at NeurIPS 2021 on Thursday, December 9th at 8:45 PM CET. IGLU stands for Interactive Grounded Language Understanding in a Collaborative Environment.

07/2021: Our paper on counterfactual explanations for GNNs was accepted to two workshops at ICML 2021: Human in the Loop Learning (HILL) and the Workshop on Algorithmic Recourse. I presented our work in the Algorithmic Recourse workshop.

06/2021: I joined Facebook AI Research for a 2021 summer internship. I will work with Emmanuel Dupoux, Dieuwke Hupkes and Evgeny Kharitonov.

04/2021: Our challenge "IGLU: Interactive Grounded Language Understanding in a Collaborative Environment" has been accepted at NeurIPS 2021! Follow our Twitter account or our website for all updates!

01/2021: I was a guest in the latest Data Skeptic podcast! We talked about automatic summarization, our work in that area and how a background in Linguistics can help you in NLP! You can find the episode in all your favourite podcast apps, for example here.

03/2020: I will be organizing SEA (Search Engines Amsterdam) this year. SEA is usually held every last Friday of the month, at Science Park Amsterdam. Usually we have two talks, one industrial, one academic. If you would like to give a talk, please get in touch.

12/2019: Our full paper "Conversations with Documents. An Exploration of Document-Centered Assistance" has been accepted at CHIIR 2020. I did this work during my internship at MSR, together with Robert Sim, Elnaz Nouri, Adam Fourney, Maarten de Rijke and Ryen White. You can read the paper here.

05/2019: I will be joining Microsoft Research in Redmond for an internship in the summer of 2019. I will be part of the KTX team (Knowledge, Technologies and Intelligent Experiences). I will work with Robert Sim and Ryen White.

09/2018: We started Inclusive AI (IAI), for MSc AI students at the University of Amsterdam. The IAI is an inclusive space for members to get non-academic help from senior peers in the field and connect with like-minded people of a similar background. I am one of the organizers and mentors.

Publications and Preprints

2022

Maartje ter Hoeve; Julia Kiseleva; Maarten de Rijke. What Makes a Good and Useful Summary? Incorporating Users in Automatic Summarization Research. In: NAACL 2022.

Ana Lucic; Maartje ter Hoeve; Gabriele Tolomei; Maarten de Rijke; Fabrizio Silvestri. CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks. In: AISTATS 2022.

Aarohi Srivastava; Abhinav Rastogi; ...; Maartje ter Hoeve; ...; Zirui Wang; Ziyi Wu. Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models. BIG Benchmark, arXiv preprint 2022.

Maartje ter Hoeve; David Grangier; Natalie Schluter. High-Resource Methodological Bias in Low-Resource Investigations.

2021

Maartje ter Hoeve; Evgeny Kharitonov, Dieuwke Hupkes, Emmanuel Dupoux. Towards Interactive Language Modeling. ACL, SPA-NLP Workshop.

Julia Kiseleva; Ziming Li; Mohammad Aliannejadi; Shrestha Mohanty; Maartje ter Hoeve; Mikhail Burtsev; Alexey Skrynnik; Artem Zholus; Aleksandr Panov; Kavya Srinet; Arthur Szlam; Yuxuan Sun; Katja Hofmann; Michel Galley; Ahmed Awadallah. NeurIPS 2021 Competition IGLU: Interactive Grounded Language Understanding in a Collaborative Environment. NeurIPS 2021, Competition Track.

Ana Lucic; Maartje ter Hoeve; Gabriele Tolomei; Maarten de Rijke; Fabrizio Silvestri. CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks. In: KDD 2021 Workshop on Deep Learning on Graphs, ICML 2021 Workshop on Algorithmic Recourse, ICML 2021 Workshop on Human in the Loop Learning.

2020

Maartje ter Hoeve; Robert Sim; Elnaz Nouri; Adam Fourney; Maarten de Rijke; Ryen White. Conversations with Documents. An Exploration of Document-Centered Assistance. In: CHIIR, Vancouver, Canada, 2020.

David Stap; Maurits Bleeker; Sarah Ibrahimi; Maartje ter Hoeve. Conditional Image Generation and Manipulation for User-Specified Content. In: CVPR (AICCW), Seattle, United States, 2020.

2019

Joris Baan; Maartje ter Hoeve; Marlies van der Wees; Anne Schuth; Maarten de Rijke. Interpreting Multi-Head Attention in Abstractive Summarization .

Joris Baan; Maartje ter Hoeve; Marlies van der Wees; Anne Schuth; Maarten de Rijke. Do Transformer Attention Heads Provide Transparency in Abstractive Summarization?. In: SIGIR (FACTS-IR), Paris, Fance, 2019.

2018

Maartje ter Hoeve; Anne Schuth; Daan Odijk; Maarten de Rijke. Faithfully Explaining Rankings in a News Recommender System.

2017

Maartje ter Hoeve; Mathieu Heruer; Daan Odijk; Anne Schuth; Martijn Spitters; Ron Mulder; Nick van der Wildt; Maarten de Rijke. Do News Consumers Want Explanations for Personalized News Rankings?. In: RecSys (FATREC), Como, Italy, 2017.

Talks

Please find a list of selected talks below:

Counterfactual Explanations for Graph Neural Networks, ICML 2021, Workshop on Algorithmic Recourse. July 24, 2021.

Automatic Summarization, Data Skeptic Podcast.

Conversations with Documents. An Exploration of Document-Centered Assistance. CHIIR 2020, Virtual Event. August 13, 2020. (Recording).

Conversations with Documents. An Exploration of Document-Centered Assistance. ICAI Meetup, Amsterdam, Netherlands. February 21, 2020.

Automatic Summarization, Lecture Information Retrieval. Amsterdam, Netherlands. March 08, 2019 (Slides).

Do News Consumers Want Explanations for Personalized News Rankings?, RecSys 2017, FATREC workshop, Como, Italy. September 5, 2017 (Slides).

Kunstmatige intelligentie concreet, Podcast (www.deuitvinders.xyz).

Teaching

Student Supervision:

2021 - Rahel Habacker, MSc Articial Intelligence, UvA, MSc thesis, Topic: Language Modeling
2020 - Michael Neely, MSc Articial Intelligence, UvA, MSc thesis, Topic: Multi-hop question answering
2020 - Justine Winkler, MSc Articial Intelligence, Radboud University, MSc thesis, Topic: Automatic Summarization
2020 - Henning Bartsch, MSc Articial Intelligence, UvA, MSc thesis, Topic: Improving user representations for news recommendation
2019 - David Stap, MSc Artificial Intelligence, UvA, MSc thesis, Topic: Conditional image generation and manipulation
2019 - Joris Baan, MSc Artificial Intelligence, UvA, MSc thesis, Topic: Transparency in abstractive summarization
2018 - David Ruhe, MSc Data Science, UvA, MSc thesis, Topic: Adversarial examples for capsule networks.
2018 - Dennis Craandijk, MSc Data Science, UvA, MSc thesis, Topic: Automatic unseen event extraction from text.
2018 - Mink Rohmer, MSc Data Science, UvA, MSc thesis, Topic: Classifying the severity of written complaints.

Courses:

2021 - Fairness, Accountability and Transparency (Guest Lecture), Master AI.
2018 - Information Retrieval 2, Master AI.
2015 - Logic Programming and Search, Bachelor AI.
2015 - Introduction to AI, Bachelor AI.
2015 - Academic Skills, Bachelor AI.
2015 - Natural Language Processing, Bachelor AI.

For supervision requests, please get in touch.

Get in touch

m [dot] a [dot] terhoeve [at] uva [dot] nl

Science Park 608b, Room 1.07, 1098 XH Amsterdam, The Netherlands