A/PROF Trevor Cohn

A/PROF Trevor Cohn

Positions

  • Natural Language Processing (Translation, Text mining, Text analytics, Machine Learning)

Overview

OverviewText1

  • Trevor Cohn is an Associate Professor in the School of Computing and Information Systems, The University of Melbourne and an Australian Research Council Future Fellow. He was previously employed at the University of Sheffield and the University of Edinburgh, and has held visiting positions at the University of Melbourne and Johns Hopkins University. His research interests focus on development of probabilistic and statistical machine learning methods for modelling natural language text, with particular interests in machine translation, parsing and grammar induction. Current projects include text analytics and rumour diffusion over social media, translating diverse and noisy text sources and speech translation. He has served on the editorial boards for Computational Linguistics and Computer Speech and Language, as area chair and reviews for major conferences including ACL, EMNLP, COLING and NIPS, as well as reviewing for several grant authorities. Trevor completed a BEng(Software) and BComm(Finance) in 2000, followed by a PhD(Engineering) in 2007, all at The University of Melbourne. Prior to commencing his position at The University of Melbourne, he was a Senior Lecturer at The University of Sheffield (2009-2014).   

Publications

Selected publications

Research

Investigator on

Additional Grant Information

    1. Efficient storage and access to text count data -- An application to unlimited order language modelling. 2016 – 2017. Google Research Award, $US85k.
    2. Low Resource Languages for Emergent Incidents (LORELEI). 2015 – 2017. DARPA subcontract, $294k.
    3. IBM Research Award. 2016. IBM Research Award, $20k.
    4. Learning Deep Semantics for Automatic Translation between Human Languages. 2016 – 2019. ARC Discovery, $450k.
    5. Adaptive Context-Dependent Machine Translation for Heterogeneous Text. 2014 – 2018. ARC Future Fellowship, $730k.
    6. WFST-based integration of ASR and MT in Spoken Language Translation. 2014 – 2015. Google Research Award, $US97k.
    7. Pheme: Computing Veracity Across Media, Languages, and Social Networks. 2014 – 2017. EU FP7, £494k.
    8. TrendMiner: Large-scale, Cross-lingual Trend Mining and Summarisation of Real-time Media Streams. 2011 – 2014. EU FP7, £529k.
    9. QuEsT: An open source tool for machine translation quality estimation. 2012. PASCAL Harvest, €20k.
    10. SLaTr: A Joint Model of Spoken Language Translation. 2011. Google Research Award, $US60k.
    11. Barista: Non-Parametric Models of Phrase-based Machine Translation. 2011 – 2012. EPSRC first grant, £127k.
    12. Grammar induction challenge. 2011. PASCAL Challenge, €10k.
    13. Discriminative Phrase-Based Statistical Machine Translation. 2007 – 2010. EPSRC with Miles Osborne. £300k.
       

Awards

Education and training

  • CILT, University of Sheffield 2013
  • PhD, University of Melbourne 2007
  • BEng, University of Melbourne 2000
  • BComm, University of Melbourne 2000

Awards and honors

  • Best Short Paper Award for paper "Learning a Lexicon and Translation Model from Phoneme Lattices", EMNLP, 2016
  • Ted Nelson Award for paper "Where's @Wally: A classification approach to geolocating users based on their social ties", ACM Hypertext, 2013
  • Best Paper Award, 2nd place, CICLING, 2013

Linkages

Supervision

Available for supervision

  • Y

Supervision Statement

  • 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. Students interested in these or related domains are welcome to apply to me for MPhil or PhD supervision. Note that I am not able to support research internships.