I am a PhD candidate in the Electrical Engineering department at the University of Washington. My advisor and committee chair is Mari Ostendorf.
In summer 2011, I was an intern at Microsoft Research in Redmond, WA. I worked with researchers from the Computational User Experiences (CUE) and Natural Language Processing (NLP) groups on normalizing and disambiguating entries of patients' chief complaints by triage nurses in emergency departments.
Before coming to UW, I worked at the Linguistic Data Consortium. Before that, I was a Computer Science and Linguistics major at Swarthmore College.
View my full CV.
My current research focus is on applications of NLP and machine learning to literacy education. In particular, I'm looking at statistical methods for identifying words, syntactic structures, and content that are difficult for a low-literacy adult to read. My thesis work looks at ways to characterize the difficulty of a text based on experiments with human subjects, ways to automatically predict the difficulty of a text from linguistic features, and ways to automatically reduce the difficulty of a text through machine learning techniques.
I am currently recruiting participants to participate in an eye tracking study to help understand text difficulty. Details are available in the call for participation.
In the summer of 2012, I co-taught a citizenship class through Literacy Source, a Seattle non-profit that offers ESL and Adult Basic Education (ABE) courses. My students had varied backgrounds and motivations, but were all preparing to apply for U.S. citizenship. We focused on history, civics, and English (reading, writing, speaking and listening) lessons.
For three years, I co-taught a one-credit seminar for undergraduate students interested in grad school. The course website for the current quarter is available online.
In the fall of 2010, I gave two guest lectures for Industrial Engineering 315, Probability and Statistics for Engineers. Check out my lecture slides on Point Estimates, Bias and Variance or Type I and Type II Errors.
From 2003 to 2007, I worked as a programmer for the Linguistic Data Consortium (LDC). I worked on the following data sets that are available through the LDC:
"Atypical Prosodic Structure as an Indicator of Reading Level and Text Difficulty," Proc. NAACL HLT, June 2013, Julie Medero, Mari Ostendorf. pdf
"Identifying Targets for Syntactic Simplification," Proc. SLaTE Workshop, September 2011, Julie Medero, Mari Ostendorf. pdf
"Analysis of Vocabulary Difficulty Using Wiktionary", Proc. SLaTE Workshop, September 2009, Julie Medero, Mari Ostendorf. pdf
"Classifying factored genres with part-of-speech histograms", Proc. NAACL HLT, pp 173-176, Sergey Feldman, Marius Marin, Julie Medero, Mari Ostendorf.pdf
"Annotation Tool Development for Large-Scale Corpus Creation Projects at the Linguistic Data Consortium", LREC 2008: Sixth International Conference on Language Resources and Evaluation, 2008, Kazuaki Maeda, Haejoong Lee, Shawn Medero, Julie Medero, Robert Parker, Stephanie Strassel.pdf
"An Efficient Approach for Gold-Standard Annotation: Decision Points for Complex Tasks", LREC 2006: Fifth International Conference on Language Resources and Evaluation, 2006, Julie Medero, Kazuaki Maeda, Stephanie Strassel, Christopher Walker.pdf
"A New Phase in Annotation Tool Development at the Linguistic Data Consortium: The Evolution of the Annotation Graph Toolkit", LREC 2006: Fifth International Conference on Language Resources and Evaluation, 2006, Kazuaki Maeda, Haejoong Lee, Julie Medero, Stephanie Strassel.pdf
"A Modular Software Architecture for Heterogeneous Robot Tasks", AAAI Mobile Robot Competition 2002: 18-23, Julie Corder, Oliver Hsu, Andrew Stout, Bruce A. Maxwell.pdf
I'm a member of the University of Washington Women's Initiative (UWWI), a group that visits local middle- and high-schools to talk to girls about engineering and what it's like to be an engineer. We combine a short presentation with hands-on activities to give girls experience in designing and building a real project.