CV

Appointments

  • Reader. 2014 – present. University of Edinburgh School of Informatics.
  • Assistant research professor. 2012 – 2015. Johns Hopkins University Department of Computer Science.
  • Assistant research scientist. 2011 – 2012. Johns Hopkins University Department of Computer Science.
  • Postdoctoral research associate. 2008 – 2010. University of Edinburgh School of Informatics.

Education

  • Ph.D. 2008. University of Maryland Department of Computer Science.
  • M.S. 2002. University of Maryland Department of Computer Science.
  • B.S. 1997. Duke University Department of Computer Science.

Papers

Refereed journal articles

    Refereed conference papers

    • Zeses Pitenis, Marcos Zampieri, and Tharindu Ranasinghe. 2020. Offensive Language Identification in Greek. In Proceedings of The 12th Language Resources and Evaluation Conference.
    • Tharindu Ranasinghe, Marcos Zampieri, and Hansi Hettiarachchi. 2019. BRUMS at HASOC 2019: Deep Learning Models for Multilingual Hate Speech and Offensive Language Identification. In Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation.
    • Tharindu Ranasinghe, Hadeel Saadany, Alistair Plum, Salim Mandhari, Emad Mohamed, Constantin Orasan, and Ruslan Mitkov. 2019. RGCL at IDAT: Deep Learning models for Irony Detection in Arabic Language. In Proceedings of the 11th annual meeting of the Forum for Information Retrieval Evaluation.
    • Alistair Plum, Tharindu Ranasinghe, Constantin Orasan, and Ruslan Mitkov. 2019. RGCL at GermEval 2019: Offensive Language Detection with Deep Learning. In Proceedings of the 15th Conference on Natural Language Processing (KONVENS 2019).
    • Tharindu Ranasinghe, Constantin Orasan, and Ruslan Mitkov. 2019. Enhancing Unsupervised Sentence Similarity Methods with Deep Contextualised Word Representations. In Proceedings of RANLP 2019.
    • Tharindu Ranasinghe, Constantin Orasan, and Ruslan Mitkov. 2019. Semantic Textual Similarity with Siamese Neural Networks. In Proceedings of RANLP 2019.
    • Hansi Hettiarachchi and Tharindu Ranasinghe. 2019. Emoji Powered Capsule Network to Detect Type and Target of Offensive Posts in Social Media. In Proceedings of RANLP 2019.
    • Alistair Plum, Tharindu Ranasinghe, and Constantin Orasan. 2019. Toponym Detection in the Bio-Medical Domain: A Hybrid Approach with Deep Learning. In Proceedings of RANLP 2019.
    • Alistair Plum, Tharindu Ranasinghe, Pablo Calleja, Constantin Orasan, and Ruslan Mitkov. 2019. RGCL-WLV at SemEval-2019 Task 12: Toponym Detection. In Proceedings of the 13th International Workshop on Semantic Evaluation.
    • Nadeesha Pathirana, Sandaru Seneviratne, Rangika Samarawickrama, Shane Wolff, Charith Chitraranjan, Uthayasanker Thayasivam, and Tharindu Ranasinghe. 2019. Concept Discovery through Information Extraction in Restaurant Domain. In Computación y Sistemas.
    • Nadeesha Pathirana, Sandaru Seneviratne, Rangika Samarawickrama, Shane Wolff, Charith Chitraranjan, Uthayasanker Thayasivam, and Tharindu Ranasinghe. 2018. Knowledge Building via Optimally Clustered Word Embedding with Hierarchical Clustering. In Proceedings of the 15th International Conference on Natural Language Processing (ICON-2018).
    • Lasitha Uyangoda, Supunmali Ahangama and Tharindu Ranasinghe. 2018. User profile feature-based approach to address the cold start problem in collaborative filtering for personalized movie recommendation.. In 2018 Thirteenth International Conference on Digital Information Management (ICDIM).

    Refereed workshop and demonstration papers

      Unpublished working papers

        Datasets

        • Fisher and CALLHOME Spanish--English speech translation. 2014. Matt Post, Gaurav Kumar, Adam Lopez, Damianos Karakos, Chris Callison-Burch, and Sanjeev Khudanpur. Released by the Linguistic Data Consortium as LDC2014T23.

        Awards

        • Notable student paper award. 2011. For EMNLP paper Training a Log-Linear Parser with Loss Functions via Softmax-Margin with Michael Auli.

        Grants

        • UKRI Centre for Doctoral Training in Natural Language Processing. 2019 – 2027. Engineering and Physical Sciences Research Council, £6.8M. Co-I with Mirella Lapata (PI), Frank Keller, Simon King, Ivan Titov, and Kenneth Heafield.
        • Amazon academic research award. 2016. $60K.
        • Google faculty research award. 2015. $52K.
        • EAGER: Formal and empirical foundations of semantics-preserving machine translation. 2013 – 2015. National Science Foundation (USA), $150K.

        Invited Talks

        • What do neural networks learn about language? 2018. Georgetown University.
        • What do neural networks learn about language? 2017. #botsBerlin deep tech meetup, hosted by Rasa NLU.
        • What do neural networks learn about language? 2017. Amazon Research.
        • Practical and theoretical problems on the frontiers of multilingual natural language processing. 2016. University of Glasgow, Department of computer science.
        • A formal model of semantics-preserving translation. 2015. University of Sheffield, Department of computer science.
        • A formal model of semantics-preserving translation. 2014. Carnegie Mellon University, Language Technologies Institute.
        • A formal model of semantics-preserving translation. 2014. University of Edinburgh Institute for Language, Cognition, and Computation.
        • Synchronous combinatory categorial grammar. 2014. University of Oxford Department of Computer Science.
        • A formal model of semantics-preserving translation. 2014. Information Sciences Institute.
        • A linguistically-informed formal model of translation. 2014. University of Illinois Department of Linguistics.
        • Statistical machine translation. 2014. Knox College Department of Computer Science.
        • A formal model of semantics-preserving translation. 2014. Toyota Technical Institute at Chicago.
        • Transduction and combinatory categorial grammar. 2013. Simon Fraser University.
        • Compact adaptable translation models on GPUs. 2013. Google.
        • Learning to translate with products of novices: Open-ended challenge problems for teaching machine translation (and AI). 2013. Information Sciences Insitute.
        • Synchronous combinatory categorial grammar. 2013. Columbia University.
        • Integrated parsing and tagging. 2012. IBM Research.
        • Generic approximate inference for very large structured NLP models. 2010. Johns Hopkins University Human Language Technology Center of Excellence.
        • Semiring parsing without parsing. 2009. University of Oxford.
        • Semiring parsing without parsing. 2009. University of Cambridge.
        • Translation model search spaces. 2009. University of Saarland.
        • Translation model search spaces. 2009. Dublin City University.
        • Translation by pattern matching. 2008. Machine Translation Marathon workshop.
        • Hierarchical phrase-based translation with suffix arrays. 2007. University of Amsterdam.
        • Hierarchical phrase-based translation with suffix arrays. 2007. University of Edinburgh.
        • Hierarchical phrase-based translation with suffix arrays. 2007. University of Pittsburgh.
        • Hierarchical phrase-based translation with suffix arrays. 2007. Carnegie Mellon University.
        • Hierarchical phrase-based translation with suffix arrays. 2007. Microsoft Research.
        • Hierarchical machine translation with suffix arrays. 2007. MITRE Corporation.
        • Statistical machine translation. 2006. Colgate University.
        • Statistical machine translation. 2005. Union College.

        Teaching

        University courses

        • Natural language understanding, generation, and machine translation. 2019 (with Rico Sennrich). Fourth-year and MSc course at the University of Edinburgh.
        • Natural language understanding. 2018. Fourth-year and MSc course at the University of Edinburgh.
        • Processing formal and natural languages. 2016 (with John Longley). Second-year course at the University of Edinburgh.
        • Machine translation. 2015, 2016, 2017. Fourth-year and MSc course at the University of Edinburgh.
        • Machine translation. 2012 (with Matt Post and Chris Callison-Burch), 2014 (with Matt Post). Graduate course at Johns Hopkins University.
        • Probability on strings, trees, and sequences. 2013, 2014. Graduate seminar at Johns Hopkins University.
        • Computer science II. 2000. Prince George's Community College.

        Tutorials and Short Courses

        • Graph formalisms for meaning representations. 2018. Half-day tutorial at EMNLP. Co-taught with Sorcha Gilroy.
        • Graph formalisms for meaning representations. 2018. One-week course at the North American Summer School on Logic, Language, and Information (NASSLLI). Co-taught with Sorcha Gilroy.
        • Word alignment. 2013. Tutorial lecture at the Eighth Machine Translation Marathon.
        • Statistical machine translation. 2012. One-week course at the North American Summer School on Logic, Language, and Information (NASSLLI).
        • Phrase-based translation. 2012. Tutorial lecture at the Seventh Machine Translation Marathon.
        • Machine translation. 2012. Tutorial lecture at NAACL Summer School on Human Language Technology.
        • Discriminative translation and transducers. 2011. Tutorial lecture at NAACL Summer School on Human Language Technology.
        • Statistical machine translation. 2010. One-week course at the European Summer School in Logic, Language and Information (ESSLLI).
        • Introduction to machine translation. 2010. Tutorial lecture at the Fifth Machine Translation Marathon.
        • Machine translation. 2010. Tutorial lecture at NAACL Summer School on Human Language Technology.
        • Introduction to machine translation. 2010. Tutorial lecture at the Fourth Machine Translation Marathon.
        • Machine translation. 2009. Tutorial lecture at NAACL Summer School on Human Language Technology.
        • Introduction to machine translation. 2009. Tutorial lecture at the Third Machine Translation Marathon.
        • Syntax-based machine translation. 2008. Tutorial lecture at the Second Machine Translation Marathon.

        Public engagement

        • Inside Google Translate. 2019. Talk at Edinburgh Science Festival.
        • When will Google Translate learn to translate poetry? 2018. Talk at Pint of Science festival.
        • Can Google Translate learn to translate poems? 2017. Talk at WordPolishers Present: Refraction, a poetry translation event at LeithLate arts festival.
        • Sutton Trust Summer School. 2015–17,19. Tutorial workshop for high school students.
        • INSPIRE summer school. 2016–17. Tutorial workshop for high school students.

        Advising

        PhD students

        • Seraphina Goldfarb-Tarrant. PhD student at University of Edinburgh since 2019.
        • Kate McCurdy. PhD student at University of Edinburgh since 2019.
        • Katarzyna Pruś. PhD student at University of Edinburgh since 2019.
        • Naomi Saphra. PhD student at University of Edinburgh since 2015, Johns Hopkins University 2013–2015.

        PhD alumni

        • Dr. Sameer Bansal. PhD, University of Edinburgh. Defended Oct 2019, to be conferred in 2020. Co-advised with Sharon Goldwater.
        • Dr. Janie Sinclair. PhD, University of Edinburgh. Defended Sep 2019, to be conferred in 2020. Co-advised with Dragan Gašević and Chris Lucas. Now postdoc at University of Amsterdam.
        • Dr. Clara Vania. PhD, University of Edinburgh. Defended Sep 2019, to be conferred in 2020. Now postdoc at New York University.
        • Dr. Nikolay Bogoychev. PhD, University of Edinburgh, 2019. Now postdoc at University of Edinburgh.
        • Dr. Sorcha Gilroy. PhD, University of Edinburgh, 2019. Now data scientist at peak.ai.
        • Dr. Federico Fancellu. PhD, University of Edinburgh, 2018. Co-advised with Bonnie Webber. Now research scientist at Samsung AI Centre.
        • Dr. Michael Auli. PhD, University of Edinburgh, 2012. Now research scientist at Facebook AI Research.

        Masters students

        • Kate McCurdy. MScR, 2019. Co-advised with Sharon Goldwater.
        • Katarzyna Pruś. MScR, 2019.
        • Moise Lubwimi. MInf, University of Edinburgh, 2018. Thesis: Investigating English generation from Abstract Meaning.
        • Justas Zemgulys. MInf, University of Edinburgh, 2018. Thesis: Deep Learning for semantic parsing.
        • Andreas Grivas. MSc, University of Edinburgh, 2017. Thesis: Parsing morphologically-rich languages using neural networks.
        • Yova Kementchedjhieva. MSc, University of Edinburgh, 2017. Thesis: Morpho-Syntactic Awareness in a Character-Level Language Model.
        • Juny Li. MSc, University of Edinburgh, 2017. Thesis: Language Model on GPU.
        • Ieva Vasiljeva. MSc, University of Edinburgh, 2017. Thesis: Problems in Graph Grammars: Exploring the Possibility of a Probabilistic Directed Acyclic Graph Automaton.
        • Ajay Viswanathan. MSc, University of Edinburgh, 2017. Thesis: Intent classification for chatbots.
        • Lena Reisinger. MInf, University of Edinburgh, 2017. Thesis: LSTM feature representation in projective and non-projective transition-based dependency parsers.
        • Arthur Verkaik. MInf, University of Edinburgh, 2017. Thesis: An interface to assist with large-scale image caption translation.
        • Evangelia Lypiridi. MSc, University of Edinburgh, 2016. Thesis: Learning to generate natural language from abstract meaning representation using a phrase-based model.
        • Despoina Christou. MSc, University of Edinburgh, 2016. Thesis: Learning to generate natural language from abstract meaning representations with neural machine translation.
        • Ida Szubert. MSc student, University of Edinburgh, 2016. Thesis: Methods for automatic alignment of abstract meaning representation and dependency grammar.
        • Sameer Bansal. MSc, University of Edinburgh, 2015. Thesis: Speech translation without speech recognition.
        • Sorcha Gilroy. MSc, University of Edinburgh, 2015. Thesis: Towards probabilistic regular graph languages.
        • Clara Vania. MSc, University of Edinburgh, 2015. Thesis: Bilingual word alignment with side information.

        Undergraduates

        • Ramona Comanescu. BSc, University of Edinburgh, 2018. Thesis: Why is AI "a sea of dudes"? Using data science and NLP methods to understand gender imbalance in a scientific community.
        • Iulia Banghea. BSc, University of Edinburgh, 2016. Thesis: Exploring methods of native language identification.

        Interns

        • Chip Huyen. BSc student at Stanford University, hosted summer 2016.
        • Pijus Simonaitis. MSc student at École Normale Supérieure de Lyon, hosted summer 2016.
        • Katarzyna Pruś. BSc student at University of Dundee, hosted summer 2015.

        Student Committees

        Examinations

        • Dr. Duygu Ataman. Thesis examiner. PhD, Universtiy of Trento, 2019.
        • Dr. Pierre Godard. Rapporteur (reviewer/ examiner). PhD, LIMSI, 2019.
        • Dr. Arturo Argueta. Thesis examiner. PhD, University of Notre Dame, 2019.
        • Dr. Stefanos Angelidis. Thesis examiner. PhD, University of Edinburgh, 2019.
        • Dr. Siva Reddy. Thesis examiner. PhD, University of Edinburgh, 2017.
        • Paul Baltescu. Thesis examiner. MScRes, Oxford University, 2016.
        • Dr. Liane Guillou. Thesis examiner. PhD, University of Edinburgh, 2016.
        • Dr. Xingyi Song. Thesis examiner. PhD, University of Sheffield, 2016.

        Consulting

        • Visiting Scientist. 2013. SDL Research.

        Service

        Research community

        • Action Editor. Transactions of the Association for Computational Linguistics 2016–.
        • Editorial Board. Computational Linguistics 2015–17.
        • Publications Chair. NAACL 2015-16.
        • Area Chair. NAACL 2019, ACL 2012, EMNLP 2009.
        • Best paper committee. EACL 2012, EMNLP 2017.
        • Program Chair. Fourth International Workshop On Crosslingual Information Access 2010.
        • Reviewer. Computational Linguistics, Journal of AI Research, Journal of Language Modeling, Natural Language Engineering. Since 2009.
        • Reviewer. ACL, COLING, CoNLL, EACL, EMNLP, ESSLLI, ICLR, IJCAI, IJCNLP, MT Summit, NAACL, NIPS, TACL, TAG+, various workshops. Since 2006.

        University and department

        • Co-director. Center for Doctoral Training in Natural Language Processing, University of Edinburgh School of Informatics. Since 2019.
        • Co-director. Center for Doctoral Training in Data Science, University of Edinburgh School of Informatics. 2017–19.
        • Postgraduate selector. Institute for Language, Cognition, and Computation. 2016–2017.
        • Undergraduate admissions officer. University of Edinburgh School of Informatics. 2015–17.
        • Executive committee. Center for Doctoral Training in Data Science, University of Edinburgh School of Informatics. 2016.
        • Academic steering committee. Center for Doctoral Training in Data Science, University of Edinburgh School of Informatics. Since 2015.
        • Organizer. NAACL Summer School in Human Language Technology. 2012.
        • Organizer. CLSP Seminar Series. 2012–2014.

        Government

        • Reviewer. Netherlands Organisation for Scientific Research. 2016.
        • Grant evaluator. European Commission, Horizon 2020 Future and Emerging Technologies program (Open track). 2016.

        Engineering Positions

        • Software Engineer. 1997–1999. IBM.