Kristen Parton
Кристен Партон  •   كريستان بارتون
PhD student
Department of Computer Science
Columbia University

I completed my PhD in October 2012, in the Natural Language Processing (NLP) group, advised by Professor Kathleen McKeown and Dr. Nizar Habash. My research lies at the intersection of NLP, machine translation (MT) and information retrieval.

Specifically, I am interested in task-oriented machine translation: problems that require translated answers, such as cross-lingual IR, cross-lingual semantic role labeling, or cross-lingual question-answering. For example, how can we evaluate tasks that require translation? Can the context of the task be used to improve or automatically post-edit the MT? Conversely, by using bilingual information from the source data and machine translated data, can we improve performance on a specific task?

In addition to my research on task-oriented MT, I have also worked on real-life, large-scale applications of machine translation during internships at Google, Yahoo! and Microsoft Research. Even though MT is often imperfect, it can allow users to access information that would otherwise be totally unreadable or unavailable. In summer 2009, my project at Google involved an indexing architecture for cross-lingual web search. The previous summer, I worked on a translation feature for At Yahoo in 2006, I worked on cross-lingual image search.


Kristen Parton, Nizar Habash, Kathleen McKeown, Gonzalo Iglesias and Adrià de Gispert. Can Automatic Post-Editing Make MT More Meaningful? EAMT 2012. Best Paper Award.

Kristen Parton, Nizar Habash, Kathleen McKeown. Lost and Found In Translation: The Impact of Machine Translated Results on Translingual Information Retrieval AMTA 2012.

Kristen Parton, Joel Tetreault, Nitin Madnani and Martin Chodorow. E-rating Machine Translation. WMT 2011.

Christian Murphy, Rita Powell, Kristen Parton and Adam Cannon. Lessons Learned from a PLTL-CS Program. Proceedings of SIGCSE 2011.

Kristen Parton and Kathleen McKeown. MT Error Detection for Cross-Lingual Question Answering. COLING 2010.

Kristen Parton, Weiyun Ma, Kathleen McKeown, and James Allan. Using Query Time Information to Improve Multilingual Search and Response Generation. In Handbook of Natural Language Processing and Machine Translation: DARPA Global Autonomous Language Exploitation. Joseph Olive (ed.) 2010.

Kristen Parton, Kathleen McKeown, Robert Coyne, Mona T. Diab, Ralph Grishman, Dilek Hakkani-Tür, Mary Harper, Heng Ji, Wei Yun Ma, Adam Meyers, Sara Stolbach, Ang Sun, Gokhan Tur, Wei Xu and Sibel Yaman. Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task. ACL 2009.

Kristen Parton, Kathleen McKeown, James Allan, and Enrique Henestroza. Simultaneous multilingual search for translingual information retrieval. CIKM 2008.

Christopher Manning and Kristen Parton. Kirrkirr: A flexible and approachable software interface to indigenous dictionaries, Institute for Research in Cognitive Science Workshop on Linguistic Databases Conference, 2001.