Jasmijn Bastings
Google (United States)(US)
Publications by Year
Research Areas
Topic Modeling, Natural Language Processing Techniques, Multimodal Machine Learning Applications, Explainable Artificial Intelligence (XAI), Adversarial Robustness in Machine Learning
Most-Cited Works
- → The elephant in the interpretability room: Why use attention as explanation when we have saliency methods?(2020)143 cited
- → The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models(2020)129 cited
- → Scaling Vision Transformers to 22 Billion Parameters(2023)118 cited
- → Graph Convolutional Encoders for Syntax-aware Neural Machine Translation(2017)78 cited
- → Scaling Up Models and Data with $\texttt{t5x}$ and $\texttt{seqio}$(2022)48 cited
- → Dissecting Recall of Factual Associations in Auto-Regressive Language Models(2023)34 cited
- → Interpretable Neural Predictions with Differentiable Binary Variables(2019)31 cited
- → “Will You Find These Shortcuts?” A Protocol for Evaluating the Faithfulness of Input Salience Methods for Text Classification(2022)28 cited
- → Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks(2018)23 cited
- → The MultiBERTs: BERT Reproductions for Robustness Analysis(2021)17 cited