Terrence D. Szymanski

About Me

I am currently a data scientist at ANZ in Melbourne, Australia. I develop analytics tools and software to facilitate institutional banking at ANZ, focusing on text analytics of financial and business news.

I was previously a postdoctoral researcher at the Insight Centre for Data Analytics at University College Dublin, involved in industry-driven research on data mining from text, with special focuses on social media and online news.

I received my PhD in Linguistics from the University of Michigan, where I studied computational linguistics and researched grammar induction from parallel text with a focus on resource-poor languages.

Interested parties may download my resume.

I am currently exploring job opportunities (NLP / data science / research). Employers and recruiters are free to contact me by email or social media.

Publications

T. Szymanski. 2017. Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings. To appear in Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL 2017). [ pdf | poster | github | bibtex ] 
@inproceedings{Szymanski:2017,
   Author = {Terrence Szymanski},
   Title = {Temporal Word Analogies: Identifying Lexical Replacement with Diachronic Word Embeddings},
   Booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
   Year = {2017} }
Y. Gurin, T. Szymanski & M. T. Keane. 2017. Discovering News Events That Move Markets. To appear in Proceedings of IEEE 2017 Intelligent Systems Conference (IntelliSys). [ bibtex ] 
@inproceedings{Gurin:2017,
   Author = {Yuri Gurin, Terrence Szymanski and Mark T. Keane},
   Title = {Discovering News Events That Move Markets},
   Booktitle = {Proceedings of the 2017 SAI Intelligent Systems Conference (IntelliSys)},
   Year = {2017} }
T. Szymanski, C. Orellana-Rodriguez, and M. T. Keane. 2016. Helping news editors write better headlines: A recommender to improve the keyword contents & shareability of news headlines. In Natural Language Processing meets Journalism Proceedings of the Workshop (NLPMJ-2016), pages 30–34. [ pdf | slides | bibtex ] 
@inproceedings{Szymanski:2016,
  Author = {Terrence Szymanski and Claudia Orellana-Rodriguez and Mark T. Keane},
  Booktitle = {Natural Language Processing meets Journalism Proceedings of the Workshop ({NLPMJ}-2016)},
  Title = {Helping News Editors Write Better Headlines: A Recommender to Improve the Keyword Contents \& Shareability of News Headlines},
  Pages = {30--34},
  Year = {2016}
}
T. Szymanski and G. Lynch. 2015. UCD: Diachronic text classification with character, word, and syntactic n-grams. In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015), pages 879–883. [ link | slides | pdf | bibtex ] 
@inproceedings{Szymanski:2015,
  Author = {Terrence Szymanski and Gerard Lynch},
  Title = {{UCD}: Diachronic Text Classification with Character, Word, and Syntactic N-grams},
  Booktitle = {Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)},
  Year = {2015}
}
T. Szymanski. 2013. Automatic extraction of linguistic data from digitized documents. In Proceedings of the Berkeley Linguistics Society, 39. [ slides | pdf | bibtex ] 
@article{Szymanski:2013,
  Author = {Terrence Szymanski},
  Title = {Automatic Extraction of Linguistic Data from Digitized Documents},
  Journal = {Proceedings of the Berkeley Linguistics Society},
  Volume = {39},
  Year = {2013}
}
T. Szymanski. 2012. Morphological Inference from Bitext for Resource-Poor Languages. PhD thesis, University of Michigan. [ pdf | bibtex ] 
@phdthesis{Szymanski:2012,
  Author = {Terrence Szymanski},
  School = {University of Michigan},
  Title = {Morphological Inference from Bitext for Resource-Poor Languages},
  Year = {2012}}
}
E. Keshet, T. Szymanski, and S. Tyndall. 2011. Ballgame: A corpus for computational semantics. Proceedings of the Ninth International Conference on Computational Semantics (IWCS 2011). [ link | pdf | bibtex ] 
@article{Keshet:2011,
  Author = {Ezra Keshet and Terrence Szymanski and Stephen Tyndall},
  Journal = {Proceedings of the Ninth International Conference on Computational Semantics (IWCS 2011)},
  Title = {BALLGAME: A Corpus for Computational Semantics},
  Year = {2011}
}

Selected Talks and Presentations

9 December, 2016. Automatic Detection of Lexical Replacement in a 20-year News Corpus. Australian Linguistics Society Annual Conference. Monash University, Melbourne, Australia. [ slides ]
3 November, 2015. Summarization. Guest Lecture for Text Analytics for Big Data, UCD CSI. [ slides ]
23 March, 2013. Language Identification in Bilingual Documents for Linguistic Data Extraction. Penn Linguistics Colloquium 37. [ slides ]
15 October, 2010. Computational Methods and Ancient "Scripts". University of Michigan HistLing Discussion Group. [ handout ]
5 December, 2008. Probabilistic Comparative Linguistic Reconstruction. University of Michigan Linguistics Student Colloquium. [ slides ]

Elsewhere

You can find me all over the internet:

What is affrication?

Affrication is a process of sound change that turns stops into affricates. (I say "Tuesday" /tuzdeɪ/ with a /t/, maybe you say "Tuesday" /tʃuzdeɪ/ with a /tʃ/.) Affrication is also my domain name and twitter handle.