I am Assistant Professor in the Computational Linguistics Group
of the University of Groningen.
I am passionate about the statistical modeling of languages, particularly in a multilingual context,
and my long-term goal is to design robust NLP algorithms that can adapt
to the large variety of linguistic phenomena observed around the world.
Among others, I work towards improving the quality of Machine Translation for challenging language pairs,
and making state-of-the art NLP models more interpretable.
As a cross-disciplinary research enthusiast, I'm interested in enhancing research on human language processing or language evolution with computational modeling tools.
Last but not least, I enjoy observing, interacting with, and finding daily inspiration in my two daughters and their trilingual minds in the making.
My research was funded by a Veni grant from the Dutch Research Council (NWO) from 2016 to 2021.
Currently, I am involved in two national-consortium projects, both funded by NWO's NWA-ORC initiative:
Interpreting deep learning models for language, speech & music (InDeep)
and
Low Resource Chat-based Conversational Intelligence (LESSEN).
Interested in my work ? Also see my Research page.
News
[Oct 2022] Two papers accepted at EMNLP:
"DivEMT: Neural Machine Translation Post-Editing Effort Across Typologically Diverse Languages",
with Gabriele Sarti, Ana Guerberof-Arenas, and Antonio Toral.
"Hyper-X: A Unified Hypernetwork for Multi-Task Multilingual Transfer",
with Ahmet Üstün, Gosse Bouma, Gertjan van Noord and Sebastian Ruder.
[Sept 2022] We're presenting a poster at the Machine Learning and the Evolution of Language Workshop (ml4evolang@JCoLE): "Challenges in Simulating the Word Order vs. Case Marking Trade-off with Neural Agents" with Yuchen Lian and Tessa Verhoef.
[Apr 2022] We've restructured the NLP course of the MSc Information Science,
adding lots of new practicals and a brand new set of project topics.
The course ended yesterday with a 4-hour session of project presentations and a Best Project Award.
A big thanks to Gabriele Sarti for embarking in this adventure with me,
and to all the students for their enthusiastic participation!
[Apr 2022] We've been awarded a new
NWO National Science Agenda grant on Low Resource Chat-based Conversational Intelligence (LESSEN)!
Looking forward to collaborating with
UvA, Leiden University, Radboud University, Rasa, Bol.com, KPN, and more...
See the official news item!
[Apr 2022] Paper published in Computational Linguistics:
"UDapter: Typology-based Language Adapters for Multilingual Dependency Parsing and Sequence Labeling",
with Ahmet Üstün, Gosse Bouma, and Gertjan van Noord.
[Apr 2022] Paper accepted at LREC:
"Evaluating Pre-training Objectives for Low-Resource Translation into Morphologically Rich Languages",
with Prajit Dhar and Gertjan van Noord.