Chris Kedzie

I am currently a 5th year Ph.D. student in the Department of Computer Science at Columbia University, working in the field of Natural Language Processing under Prof. Kathleen McKeown. My research has focused on applied machine learning for large scale, streaming news summarization. I am currently working on deep learning methods for content selection in text summarization problems. In general, I am interested in deep learning methods for text generation and text understanding.

I am currently involved in several summarization projects: Columbia's Newsblaster summarizer; sumpy: a python library for multi-document summarization; and an update summarization system for the TREC Temporal Summarization track.

Find my CV here.

This summer (2016) I will be presenting our latest work on streaming summarization at IJCAI, as well as attending the associated doctoral consortium. If you are in NYC this summer, feel free to look me up!

Last summer I interned at Microsoft Research NYC with Fernando Diaz, where we continued to work on streaming update summarization.

My research touches on linguistics, artificial intelligence, and machine learning. I tend to put most everything I do on github. I really like python.

Before being a CS person, I studied music and used to be pretty good at classical guitar and producing music for radio, film, and television.

Publications


Chris Kedzie, Kathleen McKeown, Hal Daume III.
"Content Selection in Deep Learning Models of Summarization"
in Proceedings of Empirical Methods in Natural Language Processing. 2018.
Paper     Supplemental     Code and Data

Chris Kedzie, Fernando Diaz, and Kathleen McKeown.
"Real-Time Web Scale Event Summarization Using Sequential Decision Making"
in Proceedings of the International Joint Conference on Artificial Intelligence. 2016.

Chris Kedzie, Kathleen McKeown, and Fernando Diaz.
"Predicting Salient Updates for Disaster Summarization"
in Proceedings of the 53nd Annual Meeting of the Association for Computational Linguistics. 2015.
[pdf]