CS Women Lunch

16 Dec
Wednesday, 12/16/2015 12:30pm to 2:00pm
Computer Science Building, Room 150
CS Women Event

Research abstract

Finding Good Enough: A Task-Based Evaluation of Query Biased Summarization for Cross Language Information Retrieval

Did you know that most of the content on the web is not in English? Cross-language search engines help users explore foreign language content and this is especially beneficial for monolingual users. This talk explores how the user experience can be optimized and tuned by exploiting techniques at the crossroads of machine translation, summarization, and information retrieval. Cross-language query-biased summarization involves automatically capturing relevant ideas or content in a foreign language, and summarizing that content in English. The final result is the 'gist' of the original foreign language document. In this talk, I discuss how a modified version of the PageRank algorithm can be applied to this problem in order to optimize the monolingual user experience. This work was sponsored by the Federal Bureau of Investigation under Air Force Contract FA8721-05-C-0002. Opinions, interpretations, conclusions, and recommendations are those of the authors and are not necessarily endorsed by the United States Government.

Personal abstract

First Jeneration

9/11 was during my final year of high school. I remember like it was yesterday. My peers quickly signed up to serve in the military while I decided to become a first-generation college student. World events eventually shaped parts of my career from the classes I took to the way I came to view community. Being a first-generation college student is more common these days than we often realize. I will discuss how my attitudes toward service have been nurtured over the years, tales of transitioning into and out of grad school, and pieces of advice that have helped me.