no code implementations • ICLR 2019 • Harm de Vries, Kurt Shuster, Dhruv Batra, Devi Parikh, Jason Weston, Douwe Kiela
We introduce `"Talk The Walk", the first large-scale dialogue dataset grounded in action and perception.
no code implementations • ACL 2022 • Nathan Schucher, Siva Reddy, Harm de Vries
Prompt tuning has recently emerged as an effective method for adapting pre-trained language models to a number of language understanding and generation tasks.
1 code implementation • 2 Oct 2021 • Vaibhav Adlakha, Shehzaad Dhuliawala, Kaheer Suleman, Harm de Vries, Siva Reddy
On average, a conversation in our dataset spans 13 question-answer turns and involves four topics (documents).
1 code implementation • NAACL 2021 • Torsten Scholak, Raymond Li, Dzmitry Bahdanau, Harm de Vries, Chris Pal
Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases.
no code implementations • 28 Jul 2020 • Harm de Vries, Dzmitry Bahdanau, Christopher Manning
To this end, we describe what we deem an ideal methodology for machine learning research on LUIs and categorize five common ways in which recent benchmarks deviate from it.
1 code implementation • ICCV 2021 • Boris Knyazev, Harm de Vries, Cătălina Cangea, Graham W. Taylor, Aaron Courville, Eugene Belilovsky
However, test images might contain zero- and few-shot compositions of objects and relationships, e. g. <cup, on, surfboard>.
1 code implementation • 17 May 2020 • Boris Knyazev, Harm de Vries, Cătălina Cangea, Graham W. Taylor, Aaron Courville, Eugene Belilovsky
We show that such models can suffer the most in their ability to generalize to rare compositions, evaluating two different models on the Visual Genome dataset and its more recent, improved version, GQA.
3 code implementations • 12 Dec 2019 • Dzmitry Bahdanau, Harm de Vries, Timothy J. O'Donnell, Shikhar Murty, Philippe Beaudoin, Yoshua Bengio, Aaron Courville
In this work, we study how systematic the generalization of such models is, that is to which extent they are capable of handling novel combinations of known linguistic constructs.
2 code implementations • ICLR 2019 • Dzmitry Bahdanau, Shikhar Murty, Michael Noukhovitch, Thien Huu Nguyen, Harm de Vries, Aaron Courville
Numerous models for grounded language understanding have been recently proposed, including (i) generic models that can be easily adapted to any given task and (ii) intuitively appealing modular models that require background knowledge to be instantiated.
1 code implementation • ECCV 2018 • Florian Strub, Mathieu Seurin, Ethan Perez, Harm de Vries, Jérémie Mary, Philippe Preux, Aaron Courville, Olivier Pietquin
Recent breakthroughs in computer vision and natural language processing have spurred interest in challenging multi-modal tasks such as visual question-answering and visual dialogue.
1 code implementation • 9 Jul 2018 • Harm de Vries, Kurt Shuster, Dhruv Batra, Devi Parikh, Jason Weston, Douwe Kiela
We introduce "Talk The Walk", the first large-scale dialogue dataset grounded in action and perception.
4 code implementations • 22 Sep 2017 • Ethan Perez, Florian Strub, Harm de Vries, Vincent Dumoulin, Aaron Courville
We introduce a general-purpose conditioning method for neural networks called FiLM: Feature-wise Linear Modulation.
Ranked #3 on
Visual Question Answering
on CLEVR-Humans
Image Retrieval with Multi-Modal Query
Visual Question Answering
+1
2 code implementations • 10 Jul 2017 • Ethan Perez, Harm de Vries, Florian Strub, Vincent Dumoulin, Aaron Courville
Previous work has operated under the assumption that visual reasoning calls for a specialized architecture, but we show that a general architecture with proper conditioning can learn to visually reason effectively.
3 code implementations • NeurIPS 2017 • Harm de Vries, Florian Strub, Jérémie Mary, Hugo Larochelle, Olivier Pietquin, Aaron Courville
It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected.
2 code implementations • 15 Mar 2017 • Florian Strub, Harm de Vries, Jeremie Mary, Bilal Piot, Aaron Courville, Olivier Pietquin
End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning.
3 code implementations • CVPR 2017 • Harm de Vries, Florian Strub, Sarath Chandar, Olivier Pietquin, Hugo Larochelle, Aaron Courville
Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
1 code implementation • 9 May 2016 • The Theano Development Team, Rami Al-Rfou, Guillaume Alain, Amjad Almahairi, Christof Angermueller, Dzmitry Bahdanau, Nicolas Ballas, Frédéric Bastien, Justin Bayer, Anatoly Belikov, Alexander Belopolsky, Yoshua Bengio, Arnaud Bergeron, James Bergstra, Valentin Bisson, Josh Bleecher Snyder, Nicolas Bouchard, Nicolas Boulanger-Lewandowski, Xavier Bouthillier, Alexandre de Brébisson, Olivier Breuleux, Pierre-Luc Carrier, Kyunghyun Cho, Jan Chorowski, Paul Christiano, Tim Cooijmans, Marc-Alexandre Côté, Myriam Côté, Aaron Courville, Yann N. Dauphin, Olivier Delalleau, Julien Demouth, Guillaume Desjardins, Sander Dieleman, Laurent Dinh, Mélanie Ducoffe, Vincent Dumoulin, Samira Ebrahimi Kahou, Dumitru Erhan, Ziye Fan, Orhan Firat, Mathieu Germain, Xavier Glorot, Ian Goodfellow, Matt Graham, Caglar Gulcehre, Philippe Hamel, Iban Harlouchet, Jean-Philippe Heng, Balázs Hidasi, Sina Honari, Arjun Jain, Sébastien Jean, Kai Jia, Mikhail Korobov, Vivek Kulkarni, Alex Lamb, Pascal Lamblin, Eric Larsen, César Laurent, Sean Lee, Simon Lefrancois, Simon Lemieux, Nicholas Léonard, Zhouhan Lin, Jesse A. Livezey, Cory Lorenz, Jeremiah Lowin, Qianli Ma, Pierre-Antoine Manzagol, Olivier Mastropietro, Robert T. McGibbon, Roland Memisevic, Bart van Merriënboer, Vincent Michalski, Mehdi Mirza, Alberto Orlandi, Christopher Pal, Razvan Pascanu, Mohammad Pezeshki, Colin Raffel, Daniel Renshaw, Matthew Rocklin, Adriana Romero, Markus Roth, Peter Sadowski, John Salvatier, François Savard, Jan Schlüter, John Schulman, Gabriel Schwartz, Iulian Vlad Serban, Dmitriy Serdyuk, Samira Shabanian, Étienne Simon, Sigurd Spieckermann, S. Ramana Subramanyam, Jakub Sygnowski, Jérémie Tanguay, Gijs van Tulder, Joseph Turian, Sebastian Urban, Pascal Vincent, Francesco Visin, Harm de Vries, David Warde-Farley, Dustin J. Webb, Matthew Willson, Kelvin Xu, Lijun Xue, Li Yao, Saizheng Zhang, Ying Zhang
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
no code implementations • 2 May 2015 • Harm de Vries, Jason Yosinski
The answer to this question depends on the personal preferences of the one asking it.
2 code implementations • NeurIPS 2015 • Yann N. Dauphin, Harm de Vries, Yoshua Bengio
Parameter-specific adaptive learning rate methods are computationally efficient ways to reduce the ill-conditioning problems encountered when training large deep networks.