Trevor Cohn

Room 1.30, Level 1
Centre for Neural Engineering

Associate Professor
ARC Future Fellow

Computing and Information Systems
The University of Melbourne
Language Technology and Knowledge Discovery research groups

Google Scholar

DBLP

Ph: +61 3 8344 1732

Understanding of human language by computers has been a central goal of Artificial Intelligence since its beginnings, with massive potential to improve communication, provide better information access and automate basic human tasks. My research focuses on technologies for automatic processing of human language, with several applications including automatic translation (akin to Google and Bing's translation tools). My core focus is on probabilistic machine learning modelling of language applications, particularly handling uncertain or partly observed data and structured prediction problems.

News

Melbourne will host ACL 2018 to be held in July, with Tim Baldwin, Karin Verspoor and myself serving as the local chairs.
My group had great publishing success, with 3 papers to appear at NAACL 2018 and 7 papers at ACL 2018 (details below).

Current Projects

Efficient storage and access to text count data: An application to unlimited order language modelling. 2016 – 2017. Google Research Award, $US 85k.
Learning Deep Semantics for Automatic Translation between Human Languages. 2016 – 2019. ARC Discovery with Reza Haffari, $450k.
Ariel: Analysis of Rare Incident-Event Languages. 2015 – 2018. DARPA LORELEI (sub-contract), $300k.
Adaptive Context-Dependent Machine Translation for Heterogeneous Text. 2014 – 2018. ARC Future Fellowship, $730k.
Pheme: Computing Veracity Across Media, Languages, and Social Networks. 2014 – 2017. EU FP7 with Kalina Bontcheva and others, £494k.

Selected Papers

Semi-supervised User Geolocation via Graph Convolutional Networks
Afshin Rahimi, Trevor Cohn and Timothy Baldwin. In Proceedings of ACL, 2018.
PDF

A Stochastic Decoder for Neural Machine Translation
Philip Schulz, Wilker Aziz and Trevor Cohn. In Proceedings of ACL, 2018.
PDF Code

Graph-to-Sequence Learning using Gated Graph Neural Networks
Daniel Beck, Gholamreza Haffari and Trevor Cohn. In Proceedings of ACL, 2018.
PDF Code

Deep-speare: A joint neural model of poetic language, meter and rhyme
Jey Han Lau, Trevor Cohn, Timothy Baldwin, Julian Brooke and Adam Hammond. In Proceedings of ACL, 2018.
PDF Code

Narrative Modeling with Memory Chains and Semantic Supervision
Fei Liu, Trevor Cohn and Timothy Baldwin. In Proceedings of ACL (short), 2018.
PDF Code

Towards Robust and Privacy-preserving Text Representations
Yitong Li, Trevor Cohn and Timothy Baldwin. In Proceedings of ACL (short), 2018.
PDF Code

Content-based Popularity Prediction of Online Petitions Using a Deep Regression Model
Shivashankar Subramanian, Timothy Baldwin and Trevor Cohn. In Proceedings of ACL (short), 2018.
PDF

Hierarchical Structured Model for Fine-to-coarse Manifesto Text Analysis
Shivashankar Subramanian, Trevor Cohn and Timothy Baldwin. In Proceedings of NAACL, 2018.
PDF

Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-based Sentiment Analysis
Fei Liu, Trevor Cohn and Timothy Baldwin. In Proceedings of NAACL (short), 2018.
PDF Code

What's in a Domain? Learning Domain-Robust Text Representations Using Adversarial Training
Yitong Li, Trevor Cohn and Timothy Baldwin. In Proceedings of NAACL (short), 2018.
PDF Code

Discourse-aware rumour stance classification in social media using sequential classifiers
Arkaitz Zubiaga, Elena Kochkina, Maria Liakata, Rob Procter, Michal Lukasik, Kalina Bontcheva, Trevor Cohn and Isabelle Augenstein. In Information Processing & Management, 2018.
PDF