Deep learning from less human supervision

 Although deep learning has produces state of the art results on many problems, it is a data hungry technology requiring a lot of human supervision in the form of annotated data. Potential PhD topic include learning to learn and meta-learning, active learning, semi-supervised learning, multi-task learning, transfer learning, and learning representations for NLP. Techniques include deep generative models (eg auto-encoders and generative adversarial networks) and reinforcement/imitation learning algorithms for Markov Decision Processes. The application areas are different problems in text processing, including (bu not limited to) machine translation and summarisation.

Our previous work in this area include (but is not limited to) learning to actively learn [1,2,3], multitask learning [4,5], semi-supervised learning [6].

[1] Learning How to Actively Learn by Dreaming
Thuy-Trang Vu, Ming Liu, Dinh Phung, Gholamreza Haffari
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 2019

[2] Learning to Actively Learn Neural Machine Translation [code]
Ming Liu, Wray Buntine, Gholamreza Haffari
In Proceedings of CoNLL, 2018.

[3] Learning How to Actively Learn: A Deep Imitation Learning Approach [code]
Ming Liu, Wray Buntine, Gholamreza Haffari
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018.

[4] Neural Machine Translation for Bilingually Scarce Scenarios: A Deep Multi-task Learning Approach [code]
Poorya Zaremoodi, Gholamreza Haffari
Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 2018.

[5] Adaptive Knowledge Sharing in Multi-Task Learning: Improving Low-Resource Neural Machine Translation
Poorya Zaremoodi, Wray Buntine, Gholamreza Haffari
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL), 2018.

[6] A Rate Distortion Approach for Semi-Supervised Conditional Random Fields
Y. Wang, G.R. Haffari, S. Wang, G. Mori
Advances in Neural Information Processing Systems (NIPS), 2010.