Hello!

Hi, welcome to my website! My name is Jasmijn (she/her), and I’m a research engineer at Google. Currently I’m interested in the following topics within Natural Language Processing and Machine Learning:

• Interpretability
• Fairness
• Robustness

I received my PhD from ILLC, University of Amsterdam, where I was advised by Wilker Aziz, Ivan Titov and Khalil Sima’an.

Publications

You can find my publications on Google Scholar.

https://orcid.org/0000-0002-5445-4417

Talks

• EMNLP 2020 Blackbox NLP. The Elephant in the Interpretability Room. (PDF)
• ACL 2019. Interpretable Neural Predictions with Differentiable Binary Variables (Google Slides)
• EMNLP 2017. Graph Convolutional Encoders for Syntax-Aware Neural Machine Translation (Google Slides)

Blog posts

• 1. The Annotated Encoder-Decoder. Explains implementing RNN-based NMT models in PyTorch.

CV

• 2006-2009, BSc in AI, Utrecht University.
• 2009-2012, MSc in AI, University of Amsterdam.
• 2015-2020. PhD in AI, ILLC, University of Amsterdam. Defended 8 October 2020.*
• 2019-Now, Research Engineer, Google.

Reviewing / Area Chair / Committees

I am a committee member of:

• Blackbox NLP 2021 (co-located with EMNLP 2021)

I was area chair (AC) for the following conferences:

• EACL 2021 (Machine Learning for NLP)
• NAACL 2021 (Interpretability and Analysis of Models for NLP)
• ACL 2021 (Interpretability and Analysis of Models for NLP)

I reviewed for the following conferences and workshops:

• ACL (2019, 2020)
• EMNLP (2018, 2019, 2020)
• CoNNL (2018, 2019)
• ICLR (2020)
• MT Summit (2019)
• WMT (2018, 2019)
• Analyzing and interpreting neural networks for NLP (BlackboxNLP, 2019, 2020)
• Debugging Machine Learning Models (Debug ML, ICLR Workshop, 2019)
• Workshop on Neural Generation and Translation (WNGT, 2018, 2019, 2020)
• Workshop on Representation Learning for NLP (RepL4NLP, 2020)
• Workshop on Structured Prediction for NLP (SPNLP, 2019)

Supervision

During my PhD I supervised the following students:

• J. Baptist (MSc Thesis)
• Laura Ruis (Honours Project)

Projects

• Interpretable Neural Predictions with Differentiable Binary Variables contains the HardKuma distribution that allows (hybrid) binary samples (with true zeros and ones) that allow gradients to pass through.
• Joey NMT is an easy-to-use, educational, and benchmarked NMT toolkit for novices that I developed with Julia Kreutzer.
• FREVAL is an all-fragments parser evaluation metric that I developed with Khalil Sima’an.

Contact

• You can find me on Twitter: @BastingsJasmijn.
• My code is on Github: github.com/bastings.