Hi there, I'm Edison

I'm a post-doctoral research fellow at the University of Tokyo, where I'm a member of weblab. I obtained my Ph.D. at the same lab on 2017, advised by Yutaka Matsuo. My research interests are Natural Language Processing and Representation Learning.

Although I'm often seduced by the theoretical side, I'm more of a practical guy. Check out my code releases, including my personal set of developing utils and my batch-wise Pytorch NLP Tutorial, both of which are in my GitHub.

One of my special interests is the study of affect in text. For my Ph.D. dissertation, I developed models to start exploiting opinions on videos such as product reviews extracted from YouTube. Previously, for my Master's, I developed a model and implemented a system to extract and summarize hotel and restaurant reviews about Los Lagos, Chile. I'm also interested in some arguably more complex linguistic affective phenomena, such irony and sarcasm. In the past I have also worked on plagiarism detection with my home university supervisor.

On the other hand, in recent years I have also become interested in studying document changes, or edits, which lie at the core of version control systems such as GitHub and Wikipedia. I have worked on learning edit representations that can be useful for tasks such as automatic commit message generation in GitHub, and better quality asessment of Wikipedia articles.

Feel free to drop me a line at {emarrese @ weblab dot t dot u-tokyo dot ac dot jp}.