Research

I am a researcher in Natural Language Processing just finishing my Ph.D. at the University of Ottawa. I am fascinated by the phenomenon of language as a means of communication. It is quite unbelievable how a string of words can help two individuals - two different universes - get a glimpse of shared reality for a short little while.

As a researcher I am particular interested in language as it is used in literature - both prose and poetry. One side of the story is analyzing literary language. What is a typical structure of a novel or a short story and how can it be established automatically? How can we identify a small set of central characters? What makes a good summary or book - is it the summary of its plot? some hints about the literary style and the author? is it something else entirely? The other side of the story is creating tools that help people who love literature enjoy it more naturally in digital format. To this end my current project is on creating reading recommendations.

My other recent fascination is emotions in written text. What devices do authors use to make a reader's heart skip a beat? How does emotional charge of a text affect its recall?

In the past I have worked on topics directly related to my recent interests, somewhat tangential and also completely different. My Ph.D. thesis, Topical Structure in Long Informal Documents, is an attempt to model topical structure of novels. My Master's thesis was on automatic summarization of short stories. Along the way I have worked a fair bit on automatic summarization of news and a bit on anaphora resolution.

Theses

Anna Kazantseva. (2014). Topical Structure in Long Informal Documents. Ph.D. Thesis. University of Ottawa.
The code is available here. The datasets are available here and here

Anna Kazantseva. (2006). Summarizing Short Fiction. Masters Thesis. University of Ottawa.

Publications

Anna Kazantseva and Stan Szpakowicz. (2014). Measuring Lexical Cohesion: Beyond Word Repetition. In The Proceedings of the 25th International Conference on Computational Linguistics. Dublin, Ireland.

Anna Kazantseva and Stan Szpakowicz. (2014). Hierarchical Topical Segmentation with Affinity Propagation. In The Proceedings of the 25th International Conference on Computational Linguistics. Dublin, Ireland. Code on GitHub .

Anna Kazantseva and Stan Szpakowicz. (2012). Topical Segmentation: a Study of Human Performance and a New Measure of Quality. In Human Language Technologies: Conference of the North American Chapter of the Association of Computational Linguistics, Proceedings (NAACL 2012), pp. 211-220. Montréal, Canada.

Alistair Kennedy, Anna Kazantseva, Diana Inkpen and Stan Szpakowicz. (2012). Getting Emotional about News Summarization. In Proceedings of the Canadian Conference on Artificial Intelligence, pp. 121-132. Toronto, Canada.

Anna Kazantseva and Stan Szpakowicz. (2011). Linear Text Segmentation Using Affinity Propagation. In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing (EMNLP 2011), pp. 284-293. Edinburgh, Scotland.

Anna Kazantseva and Stan Szpakowicz. (2010). Summarizing Short Stories. In Computational Linguistics 36(1), pp. 71-109.

Anna Kazantseva. (2006). An Approach to Summarizing Short Stories. Student Research Workshop at the 11th Conference of the European Chapter of the Association of Computational Linguistics (Student EACL 2006). In Conference Companion, pp. 55-63. Trento, Italy.

Anna Kazantseva and Stan Szpakowicz. (2006). Challenges in Evaluating Summaries of Short Stories. In Proceedings of the Workshop on Task-Focused Summarization and Question Answering, pp. 8-15. Sydney, Australia.

Terry Copeck, Anna Kazantseva, Alistair Kennedy, Alex Kunadze, Diana Inkpen, Stan Szpakowicz. (2008). Update Summary Update. Text Analysis Conference (TAC) 2008, Gaithersburg, Maryland, USA, November 2008

Terry Copeck, Diana Inkpen, Anna Kazantseva, Alistair Kennedy, Darren Kipp, Stan Szpakowicz. (2007). Catch What You Can. Document Understanding Workshop (DUC) 2007, Rochester, New York, USA, May 2007.

Terry Copeck, Diana Inkpen, Anna Kazantseva, Darren Kipp, Vivi Nastase and Stan Szpakowicz. (2006). Leveraging DUC. In Proceedings of the 2006 Document Understanding Conference (DUC-2006) at NLT/NAACL 2006. New York.

courtesy of webmatter.de