Scholar
Edison Marrese-Taylor
Google Scholar ID: uK_esCgAAAAJ
National Institute of Advanced Industrial Science and Technology (AIST)
Citations & Impact
Citations
1,118
H-index
14
i10-index
23
Publications
20
Co-authors
13
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Developed models to extract fine-grained opinions from product review videos and for temporal video grounding. Worked on learning edit representations that can be useful for tasks such as automatic commit message generation in GitHub, and better quality assessment of Wikipedia articles.
Research Experience
- Researcher at the National Institute of Advanced Industrial Science and Technology (AIST), member of the Language and Information Research Team (LANIRT). Visiting Assistant Professor at Matsuo-ken in The University of Tokyo.
Education
- Ph.D. from The University of Tokyo, advised by Yutaka Matsuo
Background
- Main research interests: Natural Language Processing and Representation Learning. Works on multi-modal approaches that combine natural language and video, having developed models to extract fine-grained opinions from product review videos and for temporal video grounding. Also interested in studying document changes, or edits, which lie at the core of version control systems such as GitHub and Wikipedia.
Miscellany
- Email: edison dot marrese @ aist dot go dot jp
