Intro

I am currently a Principal Member of Technical Staff at Oracle Digital Assistant, Oracle Corporation. My current focus is on intelligent chatbots, digital assistant using advanced technologies in NLP, NLU, Deep Learning.

From 2015 to 2018, I studied my PhD under the joint supervision of Assoc. Prof. Trevor Cohn and Dr. Reza Haffari. My PhD research lies on Natural Language Processing and Applied Machine Learning, particularly on Deep Learning models (e.g., sequence to sequence learning and inference) applied to neural machine translation.

Prior to coming to Melbourne, I spent approximately 7 years (2008-2015) in Singapore for studying at National University of Singapore (NUS) (Masters) and then working as a R&D enginneer at HLT department, Institute for Infocomm Research (I2R), A*STAR. Before that, I was a student/teaching & research assistant/lecturer at University of Science, Vietnam National University at Ho Chi Minh City, Vietnam. During this time, I was a research intern at National Institute of Informatics in Tokyo, Japan, working under Dr. Nigel Collier in a bio-text mining project (BioCaster).

Recent Highlights

*** On 10 May 2019, I've joined Oracle Corporation, working for Oracle Digital Assistant.

*** On 15 Feb 2019, I've submitted my thesis for final examination.

*** In Sep 2018, I joined Speak.AI (a new startup company headquartered in WA, USA) as an AI scientist, working on developing solutions for on-device conversational AI. Since May 2019, Speak.AI is a part of Oracle Corporation.

*** I was a research intern at NAVER LABS Europe (formerly as Xerox Research Centre Europe) from Mar 2018 to June 2018, working with Marc Dymetman on the project "Globally-driven Training Techniques for Neural Machine Translation".

*** Transformer-DyNet is my latest *humble* neural sequence-to-sequence toolkit (written in C++ with dynet backend). It implements Google's state-of-the-art Transformer architecture in a simplified manner. It's fast and efficient, can produce very high performance, consistently with Google's tensor2tensor or Amazon's Sockeye. This is the first C++ implementation of Transformer in DyNet (I suppose, correct me if I am wrong!).

*** I received the Google Australia PhD Travel Scholarship for my trip to EMNLP 2017. Special thanks to Google Australia.

*** I participated in the 2017 Jelinek Summer Workshop on Speech and Language Technology (JSALT) at CMU, June-August 2017, Pittsburgh, PA, USA. My main research focus will be on Neural Machine Translation conditioned on low/zero resources.

An Adaptable Task-oriented Dialog System for Stand-alone Embedded Devices
Long Duong, Vu Cong Duy Hoang, Tuyen Quang Pham, Yu-Heng Hong, Vladislavs Dovgalecs, Guy Bashkansky, Jason Black, Andrew Bleeker, Serge Le Huitouze, Mark Johnson. In Proceedings of Annual Meeting of the Association for Computational Linguistics (ACL-19) (System Demonstrations), 2019.
Abstract Video
Moment Matching Training for Neural Machine Translation - A Preliminary Study
Cong Duy Vu Hoang, Ioan Calapodescu, Marc Dymetman. In arXiv preprint, 2018.
Abstract
Improved Neural Machine Translation using Side Information
Cong Duy Vu Hoang, Gholamreza Haffari and Trevor Cohn. In Proceedings of The 16th Annual Workshop of The Australasian Language Technology Association (ALTA'18) (long, oral) (best paper award), 2018.
Abstract Code
Iterative Back-Translation for Neural Machine Translation
Cong Duy Vu Hoang, Philipp Koehn, Gholamreza Haffari and Trevor Cohn. In Proceedings of The 2nd Workshop on Neural Machine Translation and Generation associated with ACL 2018 (long, poster), 2018.
Abstract
Towards Decoding as Continuous Optimization in Neural Machine Translation
Cong Duy Vu Hoang, Gholamreza Haffari and Trevor Cohn. In Proceedings of Conference on Empirical Methods in Natural Language Processing (EMNLP'17) (long, oral), 2017.
Abstract Code
Improving Neural Translation Models with Linguistic Factors
Cong Duy Vu Hoang, Gholamreza Haffari and Trevor Cohn. In Proceedings of The 14th Annual Workshop of The Australasian Language Technology Association (ALTA'16) (long, oral) (best paper award), 2016.
Abstract
Incorporating Structural Alignment Biases into an Attentional Neural Translation Model
Trevor Cohn, Cong Duy Vu Hoang, Ekaterina Vylomova, Kaisheng Yao, Chris Dyer and Gholamreza Haffari. In Proceedings of The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT'16) (long), 2016.
Abstract Code
Incorporating Side Information into Recurrent Neural Network Language Models
Cong Duy Vu Hoang, Gholamreza Haffari and Trevor Cohn. In Proceedings of The 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT'16) (short), 2016.
Abstract Code