Supervision
Here you can find links to the PhD and MSc theses I supervised or co-supervised.
PhD
Ongoing: Bryan Eikema, Pedro Ferreira, Evegenia Ilia, Nicola De Cao, Joris Baan.
Completed
- Gonçalo Correia. 2022. Learnable Sparsity and Weak Supervision for Data-Efficient, Transparent, and Compact Neural Models
- Jasmijn Bastings. 2020. A Tale of Two Sequences: Interpretable and Linguistically-Informed Deep Learning for Natural Language Processing
- Philip Schulz. 2020. Latent Variable Models for Machine Translation and How to Learn Them
- Joachim Daiber. 2018. Typologically Robust Statistical Machine Translation
- Miloš Stanojević. 2017. Permutation Forests for Modeling Word Order in Machine Translation
MSc
- Ivo Verhoven. 2022. Inductive Biases for Morphologically Informed Neural Machine Translation
- Laurence Bont. 2022. Multilingual synthetic QA corpora generation using round-trip consistency with adapters to partially enable zero-shot cross-lingual transfer
- Nikita Bortych. 2021. Loss calibrating variational neural machine translation
- Claartje Barkhof. 2021. Taking a step back: assessing the TransformerVAE as a latent variable model first
- Mathijs Pieters. 2020. Transparency for Text Classification Models
- Lina Murady. 2020. Probabilistic Models for Joint Classification and Rationale Extraction
- Eelco van der Wel. 2020. Improving Controllable Generation with Semi-supervised Deep Generative Models
- Nuno Mota. 2019. Textual (Generalised) Any-Shot Learning - The Case of Relation Classification
- Ruben Gerritse. 2019. Co-Training Generative Neural Machine Translation Models
- Akash Raj Komarlu Narendra Gupta. 2019. Semi-supervised Morphological Reinflection using Rectified Random Variables
- Dhruba Pujary. 2019. Supervised Neural Disease Normalization
- Daan van Stigt. 2019. Neural Language Models with Latent Syntax
- Tom Pelsmaeker. 2019. Effective Estimation of Deep Generative Models of Language
- Bryan Eikema. 2018. Auto-Encoding Variational Neural Machine Translation
- Sander Bijl de Vroe. 2017. Character-level Neural Architectures for Jointly Predicting Word Alignments and Word-internal Structure in Morphologically Complex Languages