Timezone: »
Neural network-based generative language models like ELMo and BERT can work effectively as general purpose sentence encoders in text classification without further fine-tuning. Is it possible to adapt them in a similar way for use as general-purpose decoders? For this to be possible, it would need to be the case that for any target sentence of interest, there is some continuous representation that can be passed to the language model to cause it to reproduce that sentence. We set aside the difficult problem of designing an encoder that can produce such representations and, instead, ask directly whether such representations exist at all. To do this, we introduce a pair of effective, complementary methods for feeding representations into pretrained unconditional language models and a corresponding set of methods to map sentences into and out of this representation space, the reparametrized sentence space. We then investigate the conditions under which a language model can be made to generate a sentence through the identification of a point in such a space and find that it is possible to recover arbitrary sentences nearly perfectly with language models and representations of moderate size without modifying any model parameters.
Author Information
Nishant Subramani (AI Foundation)
Samuel Bowman (New York University)
Kyunghyun Cho (New York University)
Kyunghyun Cho is an associate professor of computer science and data science at New York University and a research scientist at Facebook AI Research. He was a postdoctoral fellow at the Université de Montréal until summer 2015 under the supervision of Prof. Yoshua Bengio, and received PhD and MSc degrees from Aalto University early 2014 under the supervision of Prof. Juha Karhunen, Dr. Tapani Raiko and Dr. Alexander Ilin. He tries his best to find a balance among machine learning, natural language processing, and life, but almost always fails to do so.
More from the Same Authors
-
2020 Expo Talk Panel: Scaling Data Labeling with Machine Learning »
Yuri Maruyama · Felix Lau · Nishant Subramani -
2019 Workshop: Emergent Communication: Towards Natural Language »
Abhinav Gupta · Michael Noukhovitch · Cinjon Resnick · Natasha Jaques · Angelos Filos · Marie Ossenkopf · Angeliki Lazaridou · Jakob Foerster · Ryan Lowe · Douwe Kiela · Kyunghyun Cho -
2019 Workshop: Context and Compositionality in Biological and Artificial Neural Systems »
Javier Turek · Shailee Jain · Alexander Huth · Leila Wehbe · Emma Strubell · Alan Yuille · Tal Linzen · Christopher Honey · Kyunghyun Cho -
2019 Poster: SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems »
Alex Wang · Yada Pruksachatkun · Nikita Nangia · Amanpreet Singh · Julian Michael · Felix Hill · Omer Levy · Samuel Bowman -
2019 Spotlight: SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems »
Alex Wang · Yada Pruksachatkun · Nikita Nangia · Amanpreet Singh · Julian Michael · Felix Hill · Omer Levy · Samuel Bowman -
2019 Tutorial: Imitation Learning and its Application to Natural Language Generation »
Kyunghyun Cho · Hal Daumé III -
2018 Workshop: Emergent Communication Workshop »
Jakob Foerster · Angeliki Lazaridou · Ryan Lowe · Igor Mordatch · Douwe Kiela · Kyunghyun Cho -
2018 Poster: Loss Functions for Multiset Prediction »
Sean Welleck · Zixin Yao · Yu Gai · Jialin Mao · Zheng Zhang · Kyunghyun Cho -
2017 Workshop: Emergent Communication Workshop »
Jakob Foerster · Igor Mordatch · Angeliki Lazaridou · Kyunghyun Cho · Douwe Kiela · Pieter Abbeel -
2017 Poster: Saliency-based Sequential Image Attention with Multiset Prediction »
Sean Welleck · Jialin Mao · Kyunghyun Cho · Zheng Zhang -
2016 Poster: End-to-End Goal-Driven Web Navigation »
Rodrigo Nogueira · Kyunghyun Cho -
2016 Poster: Iterative Refinement of the Approximate Posterior for Directed Belief Networks »
R Devon Hjelm · Russ Salakhutdinov · Kyunghyun Cho · Nebojsa Jojic · Vince Calhoun · Junyoung Chung -
2015 Workshop: Multimodal Machine Learning »
Louis-Philippe Morency · Tadas Baltrusaitis · Aaron Courville · Kyunghyun Cho -
2015 Poster: Attention-Based Models for Speech Recognition »
Jan K Chorowski · Dzmitry Bahdanau · Dmitriy Serdyuk · Kyunghyun Cho · Yoshua Bengio -
2015 Spotlight: Attention-Based Models for Speech Recognition »
Jan K Chorowski · Dzmitry Bahdanau · Dmitriy Serdyuk · Kyunghyun Cho · Yoshua Bengio -
2014 Poster: Identifying and attacking the saddle point problem in high-dimensional non-convex optimization »
Yann N Dauphin · Razvan Pascanu · Caglar Gulcehre · Kyunghyun Cho · Surya Ganguli · Yoshua Bengio -
2014 Poster: On the Number of Linear Regions of Deep Neural Networks »
Guido F Montufar · Razvan Pascanu · Kyunghyun Cho · Yoshua Bengio -
2014 Demonstration: Neural Machine Translation »
Bart van Merriënboer · Kyunghyun Cho · Dzmitry Bahdanau · Yoshua Bengio -
2014 Poster: Iterative Neural Autoregressive Distribution Estimator NADE-k »
Tapani Raiko · Yao Li · Kyunghyun Cho · Yoshua Bengio