Meeting notes: https://pad.inria.fr/p/g.ok3rdLX0dFe05Xs6$np_6Ojzf6LKRAfXYA17
13h45 Welcome and general news about the project
– welcome to our new post-doc: Mohit
– intern “detecting and mitigating bias in text classifier” supervised by Miguel and Luis (Link to subject: http://luisgalarraga.de/docs/InternshipNLP2021.pdf)
14h: Elisa Fromont
Neetu Kushwaha’s work (10′ + 15′)
Neetu Kushwaha’s work (10′ + 15′)
14h25: Neetu Kushwaha (20′ + 15′)
presentation of “MODE: Automated Neural Network Model Debugging via State Differential Analysis and Input Selection”. Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) Pages 175–186
presentation of “MODE: Automated Neural Network Model Debugging via State Differential Analysis and Input Selection”. Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE) Pages 175–186
15h: Mohit Mittal (50′ + 15′)
“First Steps towards Debugging VQA Systems”.
“First Steps towards Debugging VQA Systems”.
Interesting resources:
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding, NIPS, 2018 (https://dl.acm.org/doi/pdf/10.5555/3326943.3327039)
- The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision, ICLR. 2019 (https://arxiv.org/pdf/1904.12584.pdf)
- FiLM: Visual Reasoning with a General Conditioning Layer, AAAI, 2018(https://arxiv.org/pdf/1709.07871.pdf)
- Learning Conditioned Graph Structures for Interpretable Visual Question Answering,NIPS, 2018(https://arxiv.org/pdf/1806.07243.pdf)
16h15-16h25: Break
16h15-17:00 : Georgios Zervakis
“Refining BERT embeddings”
“Refining BERT embeddings”
Interesting resources
17-18h (ONLY FOR THE PERMANENT INRIA MEMBERS and Gaëlle): Discussions about HR.
