Professor Associate Dean (Research Training) Director of the ARC Centre in Cognitive Computing for Medical Technologies School of Computing and Information Systems The University of Melbourne Victoria 3010, Australia Office:  Room 3.25, Level 3, Doug McDonell Building Tel:  +61 3 8344 1363 Email:  Twitter:  @eltimster

Major Projects

Present

• Making Computers Understand Common Language about Place (ARC Discovery Project, 2017–2019)
• User-Adaptive Search and Evaluation for Complex Information-Seeking Tasks (ARC Linkage Project, 2016–2019)
• ARC Centre in Cognitive Computing for Medical Technologies (ARC ITRP, 2018–2023)
• Biochemical text mining for advancing chemical and pharmaceutical knowledge (ARC Linkage Project, 2018—2021)

Past

• Personalised Topic Modelling and Sentiment Analysis for Enhanced Information Discovery over Document Streams (ARC Linkage Project, 2013–2017)
• VetCompass: Big Data and Real-time Surveillance for Veterinary Science (ARC LIEF Project, 2016)
• Information access through web-scale question-answer pair finding, ranking and matching (ARC Future Fellowship, 2013—2016)
• Talking about Place — Tapping Human Knowledge to Enrich National Spatial Data Sets (ARC Linkage Project, 2011–2014)
• Principles, Practice, and Pragmatics of Measurement in Experimental Computer Science (ARC Discovery Project, 2011–2014)
• NICTA biomedical text mining (with Verspoor, Cavedon, Zobel, Moffat et al.)
• OLE (ARC Discovery Project, with Bird: Online Linguistic Exploration: Deeper, Faster, Broader Language Documentation, 2009–2011)
• Kubadji (ARC Discovery Project, with Zukerman, Sonenberg, Balbo and Bird: Personalised Content Delivery for Assisted Navigation of Information Rich, Physical Environments such as a Museum, 2007–2010)
• Web-scale Language Identification: All Languages Great and Small (Google Research Award, 2008–2009)
• Multilingual Unsupervised Parse Selection (Microsoft Research Asia Research Award, 2009–2010)
• Web User Forum Text Analysis (Microsoft Research Asia Research Award, 2008–2009)
• Information Delivery from Segmented Textual Data Streams (ARC Discovery Project: 2006–2008)
• Scalable Language Understanding for Japanese (joint research project with NTT Communication Science Labs., 2006–2008)
• Interactive Information Discovery and Delivery (NICTA project, with Cavedon, Stokes, Bird, Moffat, et al., 2005–2007)
• An Intelligent Search Infrastructure for Language Resources on the Web (ARC e-Research Special Research Initiative, with Bird and Hughes, 2006)
• Feature-rich Word Sense Disambiguation and Unknown Word Bootstrapping (joint research project with NTT Communication Science Labs., 2004–2006)

Publications

See my publications page for a reasonably up-to-date list of my papers (with links to most papers). My Google Scholar profile and Semantic Scholar profile are also a reasonably accurate snapshot of my publication output.

Talks

Slides from recent talks:

• Language and the Shifting Sands of Domain, Space and Time, Invited Talk at the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects, Santa Fe, USA.
• Democratic Regression, Stanford University NLP Golden Hour talk, Stanford, USA.
• Robust, Unbiased Natural Language Processing, Keynote Talk at the The Third Workshop on Representation Learning for NLP, Melbourne, Australia.
• Language Identification in the Wild, Guest Talk at the First Workshop on Multi-Language Processing in a Globalising World, Dublin, Ireland.
• Learning to Label Documents, Invited Talk at the ICML 2017 Workshop on Learning to Generate Natural Language, Sydney, Australia.
• VetCompass: Clinical Natural Language Processing for Animal Health, Invited Talk at the 2016 Clinical Natural Language Processing Workshop, Osaka, Japan.
• Multiword Expressions at the Grammar--Lexicon Interface, Invited Talk at the COLING 2016 Workshop: Grammar and lexicon: interactions and interfaces, Osaka, Japan.
• Multiword Expressions: From Theory to Practicum, Invited Talk at the ICGL 2015 Workshop: Modern Greek MWE 2015, Berlin, Germany.
• Text Mining of Social Media: Going beyond the Text and Only the Text, Invited Talk at the ACL 2015 Workshop on Noisy User-generated Text (W-NUT), Beijing, China.
• Composed, Distributed Reflections on Semantics and Statistical Machine Translation, Invited talk at the Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (SSST-8 2014).
• Semantic Analysis of Social Media, Keynote talk at the Third Joint Conference on Lexical and Computational Semantics (*SEM 2014).

Resources

Online systems

• Twitter user geolocator: predict the location of a Twitter user based on the text of their recent posts, and their user profile [developed in collaboration with Bo Han and Paul Cook]
• FOKS: an intelligent dictionary interface for Japanese, intended to help learners of Japanese look up unknown words without having to dust off their kanji dictionary [developed in collaboration with Lars Yencken and Slaven Bilac]
• Kanji Tester: an adaptive Japanese learning environment, specifically targeted at those swatting for the JLPT 3 and 4 exams [developed in collaboration with Lars Yencken]
• SimSearch: a visual kanji search interface, based on similarity with known kanji [developed in collaboration with Lars Yencken]

Software

• pigeo: an automatic geotagging tool, based on text- and graph-based methods [developed in collaboration with Afshin Rahimi and Trevor Cohn]
• LexSemTM: code for training topic models to estimate word sense distributions at scale [developed in collaboration with Andrew Bennett, Jey Han Lau, Francis Bond and Diana McCarthy]
• polyglot: a language identification toolkit for multilingual documents [developed in collaboration with Marco Lui and Jey Han Lau]
• Toolkit for evaluating topic coherence and topic model quality: toolkit for evaluating the semantic coherence of individual topics and overall topic models, as described in our EACL 2014 paper [developed in collaboration with Jey Han Lau and Dave Newman]
• Twitter user geolocator: trained models and full code to replicate the Twitter user geolocation experiments published in our ACL 2013 demo paper [developed in collaboration with Bo Han and Paul Cook]
• HDP-based word sense induction system: toolkit for inducing word senses based on a Hierarchical Dirichlet Process (HDP) [developed in collaboration with Jey Han Lau and Paul Cook]
• On-line Topic Modeller: implementation of an on-line topic modeller for trend analysis [developed in collaboration with Jey Han Lau]
• langid.py: fast, accurate standalone language identification toolkit; also versions of the pre-trained identifier in C and Javascript [developed in collaboration with Marco Lui]
• SiteScraper: automatically scrapes data from websites based on a handful of sample URLs and strings of interest [developed in collaboration with Richard Penman and David Martinez]
• Hydrat: Python library for text categorisation/language identification [developed in collaboration with Marco Lui]
• Malay tokeniser/lemmatiser: lex/perl tools for tokenising and lemmatising Malay text

Datasets

• Pre-trained doc2vec models for English (described in Lau and Baldwin, 2016)
• LexSemTM (largely) all-vocabulary trained topic models for English (described in Bennett et al., to appear)
• CQADupStack dataset of duplicate questions from StackExchange (described in Hoogeveen et al., 2015)
• Financial agreement named entity dataset (described in Salinas et al., 2015)
• City label set for user geolocation (described in Han et al., 2014; with thanks to Mark Dredze)
• W-NUT 2015 Shared Task on Lexical Normalisation for English Tweets (described in Baldwin et al., 2015)
• Locative Expressions in Social Media Text dataset (described in Liu et al., 2014)
• Novel sense dataset (described in Cook et al., 2014)
• Twitter and Web lexical sample sense annotations (described in Gella et al., 2014)
• Twituser language identification dataset (described in Lui and Baldwin, 2014)
• Topics annotated for observed coherence (described in Lau et al., 2014)
• Multilingual language identification dataset (described in Lui et al., 2014)
• Lexical normalisation dictionary (described in Han et al., 2012)
• Japanese SemCor (described in Bond et al., 2012)
• Multi-domain language identification dataset (from Lui and Baldwin, 2011)
• Topic label dataset (described in Lau et al., 2011)
• Lexical normalisation dataset (described in Han and Baldwin, 2011, incorporating corrections from Jacob Eisenstein); (old version: v1.1)
• Multilingual language identification dataset (as used in the ALTA-2010 Shared Task, and described in Baldwin and Lui, 2010)
• Web user forum thread and post structure dataset (described in Kim et al., 2010 and Wang et al., 2010)
• Topic coherence topics and human judgements (described in Newman et al., 2012)
• Language identification dataset (described in Baldwin and Lui, 2010)
• Case and punctuation restoration dataset (described in Baldwin and Joseph, 2009)
• Satire document collection (described in Burfoot and Baldwin, 2009)
• Tagalog predicate-argument parsing dataset (described in Mistica and Baldwin, 2009)
• Pooled kanji similarity dataset (described in Yencken and Baldwin, 2008)
• Noun-noun compound semantic relations (described in Kim and Baldwin, 2008)
• Compound nominalisation interpretation (described in Nicholson and Baldwin, 2008)
• Deep lexical acquisition of English verb-particle constructions (described in Baldwin, 2008)
• Parsing and WSD dataset (described in Agirre et al., 2008) — email me for access details
• Kanji similarity dataset (described in Yencken and Baldwin, 2006)
• Japanese grapheme-phoneme alignment data (described in Baldwin and Tanaka, 1999)

Miscellaneous

• Multiword expressions (companion page associated with Handbook of NLP chapter)

Teaching

Present

• COMP10001 Foundations of Computing (Semester 1, 2018; co-lectured with Nic Geard)

Past

• COMP30027 Machine Learning (Semester 1, 2017; co-lectured with Karin Verspoor)
• Lecture series on Social Media and Text Analytics presented as part of the International Summer School on Web Science and Technology (2016)
• Series of guest lectures on Text Analysis of Social Media presented as part of Language Technology II (Saarland University, August, 2014)
• COMP10001 Foundations of Computing (Semester 1, 2014—2017; co-lectured with Andrew Turpin and Egemen Tanin)
• COMP10001 Foundations of Computing (Semester 1, 2012—2013)
• COMP90051 Statistical and Evolutionary Learning (Semester 2, 2011; co-lectured with Michael Kirley)
• COMP30018 Knowledge Technologies (2010—2012)
• INFO10001 Informatics 1 (2008—2011)
• Empirical Approaches to Multilingual Lexical Acquisition (Saarland University, Winter, 2008; taught as part of the Erasmus Mundus LCT Masters program)
• 433-352 Data on the Web (2006—2009)
• 433-484/684 Machine Learning (2006— 2008)
• ESSLLI 2006 course on Data-Driven Methods for Acquiring Linguistic Information (with Aline Villavicencio, Anna Korhonen and Valia Kordoni)
• Lexical semantics course convener and co-lecturer for ACL/HCSNet Advanced Program in Natural Language Processing (2006)
• 433-253 Algorithms and Data Structures (2006—2007; co-lectured with Linda Stern)
• 433-395 Advanced Topic in Computer Science (2005)
• 433-680 Machine Learning (2005)
• An Introduction to Computational Word Learning (Stanford University, Fall Quarter, 2003)

Staff

Present

• Bahar Salehi (Research Fellow 2017—)
• Afshin Rahimi (Research Fellow 2018—)

Past

• Julian Brooke (McKenzie Postdoctoral Fellow 2015—2017)
• Andrew Bennett (Research Associate 2016—2017)
• Huizhi Liang (Research Fellow 2014—2016)
• Joel Nothman (Research Fellow 2015—2016)
• Angelos Molfetas (Research Fellow 2014)
• Yvette Graham (Research Fellow 2012—2014)
• Paul Cook (McKenzie Postdoctoral Fellow 2011—2014)
• Jey Han Lau (Research Fellow 2013)
• Rebecca Dridan (Research Fellow working on OLE 2009—2011)
• Gintarė Grigonytė (Visiting Research Fellow 2011)
• Su Nam Kim (Research Fellow working on LangID and ILIAD 2009—2010)
• Patrick Ye (Research Fellow working on Kubadji 2009—2010)
• David Martinez (Research Fellow working on ILIAD 2007—2009)
• Marco Lui (Research Assistant working on ILIAD and LangID 2009—2010)
• Richard Penman (Research Assistant working on ILIAD 2008—2009)
• Shlomo Berkovsky (Research Fellow 2007—2008)
• Kapil Gupta (Research Fellow 2009)

Students

Present

• Tatsuya Aoki (visiting PhD student from Tokyo Institute of Technology)
• Shraey Bhatia (PhD student; co-supervised with Jey Han Lau)
• Fajri (PhD student; co-supervised with Jey Han Lau)
• Adel Foda (PhD student; co-supervised with Jey Han Lau)
• Brian Hur (PhD student; co-supervised with James Gilkerson, Laura Hardefeldt, and Karin Verspoor)
• Anirudh Joshi (PhD student; co-supervised with Richard Sinnott and Cecile Paris)
• Haonan Li (PhD student; co-supervised with Martin Tomko and Maria Vasardani)
• Yitong Li (PhD student; co-supervised with Trevor Cohn)
• Fei Liu (PhD student; co-supervised with Trevor Cohn)
• Nitika Mathur (PhD student; co-supervised with Trevor Cohn)
• Navnita Nandakumar (MSc(CS) student; co-supervised with Bahar Salehi)
• Aili Shen (PhD student; co-supervised with Jianzhong Qi and Bahar Salehi)
• Shivashankar Subramanian (PhD student; co-supervised with Trevor Cohn)
• Ekaterina Vylomova (PhD student; co-supervised with Trevor Cohn)
• Jinxiang Wang (MSc(CS) student)
• Jun Wang (MSc(CS) student; co-supervised with Graeme Gange)

Past

• Doris Hoogeveen (PhD student; co-supervised with Karin Verspoor)
• Afshin Rahimi (PhD student; co-supervised with Trevor Cohn)
• Ned Letcher (PhD student; co-supervised with Emily Bender)
• Jingyuan Zhang (MIT student)
• Jim Breen (PhD student; co-supervised with Francis Bond)
• Steven Xu (MSc(CS) student; co-supervised with Jey Han Lau)
• Katharine Cheng (MSc(CS) student; co-supervised with Karin Verspoor)
• Richard Fothergill (PhD student — currently working at rome2rio)
• Viet Nguyen (MSc(CS) student; co-supervised with Julian Brooke)
• Shraey Bhatia (MSc(CS) student; co-supervised with Jey Han Lau — currently a PhD student at The University of Melbourne)
• King Chan (completed PGDip studies in 2017; co-supervised with Julian Brooke)
• Ionut-Teodor Sorodoc (visiting Masters student in 2016; co-supervised with Jey Han Lau)
• Bahar Salehi (completed PhD 2016; co-supervised with Paul Cook)
• Andrew Bennett (completed MSc(CS) 2016; co-supervised with Jey Han Lau, Francis Bond, Diana McCarthy and Paul Cook — currently a PhD student at Cornell University)
• Liang Han (completed MIT 2016)
• Michael Niemann (completed PhD 2015; co-supervised with Henry Linger — currently working at Deakin University)
• Julio Salinas (completed MIT 2015; co-supervised with Karin Verspoor)
• Marco Lui (completed PhD 2015 — currently working at rome2rio)
• Li Wang (completed PhD 2015; co-supervised with Su Nam Kim — currently working at Evernote)
• Nitika Mathur (completed MSc(CS) 2014; co-supervised with Yvette Graham)
• Bo Han (completed PhD 2014; co-supervised with Paul Cook — currently working at IBM Research)
• Xiwei Wang (completed MSc(CS) 2014; co-supervised with Yvette Graham — currently working at Alibaba)
• Andrew Chester (completed MSc(CS) 2014; co-supervised with Tony Wirth — currently working at Deloitte)
• Jared Willett (completed MSc(CS) 2012; co-supervised with David Martinez and Angus Webb)
• Siming Wang (completed PGDip 2013; co-supervised with Alistair Moffat)
• Meladel Mistica (completed PhD 2013; external supervisor — currently working at Intel SDI Science Team)
• Spandana Gella (completed MSc(CS) 2013; co-supervised with Paul Cook — currently a PhD student at Edinburgh University)
• Jey Han Lau (completed PhD 2013; co-supervised with Dave Newman — currently working at IBM Research)
• Clint Burford (completed PhD 2013; co-supervised with Steven Bird — currently working at Evernote)
• Willy Yap (completed PhD 2013; co-supervised with Tara McIntosh — currently working at Sensis)
• Luke Parkinson (MSc(CS); co-supervised with Paul Cook — currently working at Microsoft)
• Matěj Korvas (completed MSc(CS) 2012 — currently working at Charles University)
• Igor Tytyk (completed MSc(CS) 2012 — currently working at Grammarly)
• Andrew MacKinlay (completed PhD 2012 — currently working at IBM Research)
• Karl Grieser (completed PhD 2012 — currently working at Sensis)
• Ned Letcher (completed BSc(Hons) 2010 — currently PhD student at UniMelb)
• Lars Yencken (completed PhD 2010 — currently working at 99designs)
• Marco Lui (completed BCS(Hons) 2009 — currently working at Rome2rio)
• Ben White (completed MIT 2009)
• Li Wang (completed MIT 2009 — currently working at Evernote)
• Patrick Ye (completed PhD 2009 — currently working at Amazon)
• Lejoe Kuriakose (completed MEDC 2008)
• Paul Joseph (completed MSSE 2008)
• Su Nam Kim (completed PhD 2008 — currently working at Monash University)
• Michael Yang (completed BCS(Hons) 2007)
• Sumukh Ghodke(completed MSSE 2007)
• Phil Blunsom (completed PhD 2007 — currently working at Oxford University)
• Edward Ivanovic (completed Masters 2007 — currently working at Deutsche Bank)
• Aidan Furlan (completed BCS(Hons) 2006)
• Karl Grieser (completed BSc(Hons) 2006 — currently working at Sensis)
• Rebecca Dridan (completed Masters 2006 — currently working at the University of Oslo)
• Jeremy Nicholson (completed BCS(Hons) 2005 — currently working at UniMelb)

Interested in pursuing natural language processing research at The University of Melbourne? Contact me directly, making sure to include a CV and description of your research interests.

UniMelb Administration

Present

• Associate Dean (Research Training) (2017—)
• CIS Education Committee (2008—)

Past

• Chair of the East Asia Regional Study Group (2016—2017)
• Member of Arts Faculty Board (2015)
• Deputy Head of Department (2011—2012)
• Teaching Committee chair (2010—2012)
• School of Engineering Education Committee (2010—2012)
• CIS Faculty of Science liaison (Science APC/PGPC: 2005—2011)
• CSSE Research Committee (2008—2011)
• CSSE Postgraduate Coursework Programmes Committee chair (2007-2009)
• School of Engineering IT Advisory Group (2009)
• Honours/PGDip Coordinator (2005-2007)
• Publications Liaison (2005-2007)
• Member of Science Tools working group, Faculty of Science (2007)

Professional Activities

Present

• Programme co-chair of The 4th Workshop on Noisy User-generated Text (W-NUT)
• Permanent Member of the International Committee on Computational Linguistics (2014—)
• Advisory Board for ACL SIGLEX (Special Interest Group on the Lexicon) (2014—)
• Advisory Board for ACL SIGDAT (Special Interest Group for linguistic data and corpus-based approaches to NLP) (2014—)
• Associate Editor for AI Access books (2013—)
• Editorial board of Transactions of the Association for Computational Linguistics (2015—)
• Tutorial Chair for IJCNLP/EMNLP 2019

Past (highlights)

• Honorary Member of the Australian Computer Society (2015—2018)
• Workshop Chair for COLING 2018
• Local Chair for ACL 2018
• Co-organiser of SemEval 2017 Task 3: Community Question Answering
• Programme co-chair of The 3rd Workshop on Noisy User-generated Text (W-NUT)
• Programme co-chair of The 2nd Workshop on Noisy User-generated Text (W-NUT)
• Programme co-chair of EMNLP 2015 workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics
• Programme co-chair of CIKM 2015 workshop on Topic Models: Post-Processing and Applications
• Workshop Chair for COLING 2014
• Australasian Language Technology Association President (2011—2012) and Secretary (2013—2014)
• Information Officer for ACL SIGLEX (Special Interest Group on the Lexicon) (2010—2013)
• Programme co-chair for EMNLP 2013
• Programme co-chair for *SEM 2013
• Guest editor of Special Issue of Linguistic Issues in Language Technology on the Interaction between Linguistics and Computational Linguistics
• Guest editor of the Special Issue of Computational Linguistics on Prepositions in Applications
• Co-chair of the EACL 2009 Workshop on the Interaction between Linguistics and Computational Linguistics: Virtuous, Vicious or Vacuous?
• Editorial board of Computational Linguistics (2006—2008)
• Workshop Chair for IJCNLP 2008
• Local Chair for PACLING 2007
• Programme Chair for the ACL 2007 Workshop on Deep Linguistic Processing
• Co-organiser of the Inaugural Workshop on Computational Japanese Studies
• Lexical semantics Theme Convener for ACL/HCSNet Advanced Program in Natural Language Processing
• Publicity Chair for COLING/ACL 2006
• Programme Chair for Frontiers in Linguistically Annotated Corpora 2006
• Programme Chair for the Third ACL-SIGSEM Workshop on Prepositions (at EACL 2006)
• Programme Chair for the Australasian Language Technology Workshop 2005
• Programme Chair for the ACL-SIGLEX Workshop on Deep Lexical Acquisition (at ACL 2005)

Random Miscellania

In the news:

• New Scientist News, The Times, Daily Mail, Digital Trends, NVIDIA, InfoSurHoy, la Repubblica, BBC Radio 4: Deep-speare — A joint neural model of poetic language, meter and rhyme (7/2018)
• ABC News: Can we Replace Red Symons with a Robot? (3/10/2017)
• Crikey: How can You Tell if a Tweet is Credible? (6/3/2017)
• Farrago: The Revolution Will Be Computerised (29/8/2016)
• Tech Exec: The Fourth Revolution: Artificial Intelligence (29/1/2016)
• MIT Technology Review: King – Man + Woman = Queen: The Marvelous Mathematics of Computational Linguistics (17/9/2015)
• NCI News: Real-time Twitter Mining (30/9/2014)
• The Age: The Rise of Artificial Intelligence (23/1/2014)
• Oregonian: Tweet Talk (24/6/2011)
• Sydney Morning Herald: Big Brains Coming back to Melbourne (6/12/2005)
• UniNews: Reversing the Brain Drain (14/11/2005)

In a moment of weakness, I signed up for LinkedIn.

For the trivia lovers, here is my (almost certainly outdated) full CV.