Kaixin Ma, Filip Ilievski, Jonathan Francis and

Yonatan Bisk, Eric Nyberg, Alessandro Oltramari

Keywords Abstract Paper

Max Schwarzer, Ankesh Anand, Rishab Goel and

R Devon Hjelm, Aaron Courville, Philip Bachman

Keywords Abstract Paper

Representation Learning, Self-Supervised Learning, Reinforcement Learning, Sample Efficiency

Marcin Andrychowicz, Anton Raichuk, Piotr Stanczyk and

Manu Orsini, Sertan Girgin, Raphaël Marinier, Hussenot Hussenot-Desenonges, Matthieu Geist, Olivier Pietquin, Marcin Michalski, Sylvain Gelly, Olivier Bachem

Keywords Abstract Paper

continuous control, Reinforcement learning

Beining Han, Chongyi Zheng, Harris Chan and

Keiran Paster, Michael Zhang, Jimmy Ba

Keywords Abstract Paper

reinforcement learning and planning, domain adaptation, representation learning

Xavier Bouthillier, Pierre Delaunay, Mirko Bronzi and

Assya Trofimov, Brennan Nichyporuk, Justin Szeto, Nazanin Mohammadi Sepahvand, Edward Raff, Kanika Madan, Vikram Voleti, Samira Ebrahimi Kahou, Vincent Michalski, Tal Arbel, Chris Pal, Gael Varoquaux, Pascal Vincent

Keywords Abstract Paper

Xavier Bouthillier, Pierre Delaunay, Mirko Bronzi and

Assya Trofimov, Brennan Nichyporuk, Justin Szeto, Nazanin Mohammadi Sepahvand, Edward Raff, Kanika Madan, Vikram Voleti, Samira Ebrahimi Kahou, Vincent Michalski, Tal Arbel, Chris Pal, Gael Varoquaux, Pascal Vincent

Keywords Abstract Paper

Bryan Wilder, Laura Onasch-Vera, Graham Diguiseppi and

Robin Petering, Chyna Hill, Amulya Yadav, Eric Rice, Milind Tambe

Keywords Abstract Paper

Joel Ye, Dhruv Batra Georgia Tech &, Facebook AI Research and

Erik Wijmans, Abhishek Das

Keywords Abstract Paper

Manu Orsini, Anton Raichuk, Leonard Hussenot and

Damien Vincent, Robert Dadashi, Sertan Girgin, Matthieu Geist, Olivier Bachem, Olivier Pietquin, Marcin Andrychowicz

Keywords Abstract Paper

theory, reinforcement learning and planning

Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal and

Hugo Larochelle, Animesh Garg, Florian Shkurti

Keywords Abstract Paper

Jixuan Wang, Kuan-Chieh Wang, Frank Rudzicz, Michael Brudno

Keywords Abstract Paper

machine learning, transformers, meta learning, language, transfer learning

Yada Pruksachatkun, Jason Phang, Haokun Liu and

Phu Mon Htut, Xiaoyi Zhang, Richard Yuanzhe Pang, Clara Vania, Katharina Kann, Samuel R. Bowman

Keywords Abstract Paper

Intermediate-Task Learning, natural tasks, data-rich task, intermediate-task training

Gaurav Mittal, Chang Liu, Nikolaos Karianakis and

Victor Fragoso, Mei Chen, Yun Fu

Keywords Abstract Paper

auto ml, hyperparameter optimization, meta learning, task aware, hyperband, hyperparameters, warm start, image classication, resnet, shufflenet

Prathyusha Jwalapuram, Shafiq Joty, Youlin Shen

Keywords Abstract Paper

pronoun translations, pronoun translation, neural training, backtranslation

Dong-Ho Lee, Rahul Khanna, Bill Yuchen Lin and

Seyeon Lee, Qinyuan Ye, Elizabeth Boschee, Leonardo Neves, Xiang Ren

Keywords Abstract Paper

sequence tasks, NLP tasks, named recognition, relation extraction

Shailza Jolly, Tobias Falke, Caglar Tirkaz, Daniil Sorokin

Keywords Abstract Paper

Oindrila Saha, Sandeep Mishra

Keywords Abstract Paper

Saliency, Recursive Supervision, Deep Supervision, Convolutional Neural Networks, Deep Learning

Wanrong Zhu, Xin Wang, Pradyumna Narayana and

Kazoo Sone, Sugato Basu, William Yang Wang

Keywords Abstract Paper

visually generation, vision-and-language tasks, cider, utilities

Qiang Zhang, Aldo Lipani, Omer Kirnap, Emine Yilmaz

Keywords Abstract Paper

Sequential, Network, and Time-Series Modeling

Bill Yuchen Lin, Dong-Ho Lee, Ming Shen and

Ryan Moreno, Xiao Huang, Prashant Shiralkar, Xiang Ren

Keywords Abstract Paper

Named Recognition, NER, supervision, label-efficient models

Yunzhi Zhang, Pieter Abbeel, Lerrel Pinto

Keywords Abstract Paper

Yi Huang, Junlan Feng, Min Hu and

Xiaoting Wu, Xiaoyu Du, Shuo Ma

Keywords Abstract Paper

Dialogue Systems, multi-domain task, new adaptation, domain adaptation

Disi Ji, Robert L. Logan, Padhraic Smyth, Mark Steyvers

Keywords Abstract Paper

Like Hui, Misha Belkin

Keywords Abstract Paper

classification, experimental evaluation, square loss vs cross-entropy, large scale learning

Jan-Matthis Lueckmann, Jan Boelts, David Greenberg and

Pedro Goncalves, Jakob Macke

Keywords Abstract Paper

Taeuk Jang, Feng Zheng, Xiaoqian Wang

Keywords Abstract Paper

Jared Lichtarge, Chris Alberti, Shankar Kumar

Keywords Abstract Paper

neural nmt, neural, example scoring, gec

Tong Zhu, Haitao Wang, Junjie Yu and

Xiabing Zhou, Wenliang Chen, Wei Zhang, Min Zhang

Keywords Abstract Paper

Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras and

Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, Yejin Choi

Keywords Abstract Paper

Ziqian Zeng, Rashidul Islam, Kamrun Naher Keya and

James Foulds, Yangqiu Song, Shimei Pan

Keywords Abstract Paper

Measuring predictability of real world phenomena based on social media, e.g., spanning politics, finance, and health

Maarten Buyl, Tijl De Bie

Keywords Abstract Paper

Fairness, Equity, Justice, and Safety

Roy Schwartz, Gabriel Stanovsky, Swabha Swayamdipta and

Jesse Dodge, Noah A. Smith

Keywords Abstract Paper

inference, early decisions, costly retraining, Job Model

Aritra Ghosh, Neil Heffernan, Andrew S. Lan

Keywords Abstract Paper

knowledge tracing, item response theory, personalized learning, monotonic attention

Yair Schiff, Brian Quanz, Payel Das, Pin-Yu Chen

Keywords Abstract Paper

deep learning

Shantanu Jaiswal, Dongkyu Choi, Basura Fernando

Keywords Abstract Paper

Biologically inspired vision, Primate visual development, Greedy layer-wise training, Supervised training approaches

Johan Obando Ceron, Pablo Samuel Castro

Keywords Abstract Paper

Reinforcement Learning and Planning, Deep RL

Andrew Gaut, Tony Sun, Shirlyn Tang and

Yuxin Huang, Jing Qian, Mai ElSherief, Jieyu Zhao, Diba Mirza, Elizabeth Belding, Kai-Wei Chang, William Yang Wang

Keywords Abstract Paper

Relation Extraction, Automated Construction, name anonymization, data augmentation

Wangshu Zhang, Junhong Liu, Zujie Wen and

Yafang Wang, Gerard de Melo

Keywords Abstract Paper

Sebastien Racaniere, Andrew Lampinen, Adam Santoro and

David Reichert, Vlad Firoiu, Timothy Lillicrap

Keywords Abstract Paper

Deep Reinforcement Learning, Automatic Curriculum

Lyujian Lu, Hua Wang, Saad Elbeleidy, Feiping Nie

Keywords Abstract Paper

alzheimer's disease, l1-norm minmax, longitudinal data, imaging biomarker, representation learning, longitudinal enrichment