Jessica Ouyang (Columbia University) “Adapting Automatic Summarization to New Sources of Information”
3400 N. Charles Street
Abstract
English-language news articles are no longer necessarily the best source of information. The Web allows information to spread more quickly and travel farther: first-person accounts of breaking news events pop up on social media, and foreign-language news articles are accessible to, if not immediately understandable by, English-speaking users. In this talk, I will give an overview of my dissertation work on adapting automatic summarization techniques to handle these new sources of information, focusing on summarizing online narratives of personal experience and cross-lingual summarization for low-resource languages, and suggest some further summarization and text generation tasks to explore.
Biography
I am a final-year PhD candidate and NSF IGERT Fellow in the Natural Language Processing Group at Columbia University, supervised by Prof. Kathy McKeown. My research is in automatic summarization of non-traditional genres, such as blog entries, recorded conversations, and non-English documents, and I am generally interested in how summarization and related natural language technologies affect the accessibility of information.