Philippe Laban
Philippe is a Ph.D. Candidate in Computer Science at UC Berkeley, advised by Marti Hearst and John Canny.

Philippe's work revolves around NewsLens project, applying the latest NLP technology to the news domain, thinking of what news interfaces could look like in the not so distant future. Do check out the demo, also available on the Play and Apple stores.

Through this journey, some areas of focus have been: summarization, simplification, entity linking, chatbots.

I have an interest in framing NLP problems in an unsupervised setting, and seeing how far we can push current NLP models without any training data (summarization, headline grouping, simplification, etc.), often performing on par with supervised methods, and sometimes outperforming them.
Teaching / Mentoring
I have been a TA (a.k.a. GSI in UCB lingo) for: I enjoyed leading discussions and lectures, creating homeworks from scratch, and interacting with brilliant students.

I have also mentored 10+ undegraduate students in their first steps doing research. If you are an undergraduate student interested in research at the intersection of NLP and News, feel free to contact me.
Peer-Reviewed Publications
Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text
Philippe Laban, Tobias Schnabel, Paul N. Bennett, Marti A. Hearst
Association for Computational Linguistics (ACL), 2021 - Long Paper
Can Transformer Models Measure Coherence In Text? Re-Thinking the Shuffle Test
Philippe Laban, Luke Dai, Lucas Bandarkar, Marti A. Hearst
Association for Computational Linguistics (ACL), 2021 - Short Paper
News Headline Grouping As A Challenging NLU Task
Philippe Laban, Lucas Bandarkar, Marti A. Hearst
North American Chapter of the Association for Computational Linguistics (NAACL), 2021
The Summary Loop: Learning to Write Abstractive Summaries Without Examples
Philippe Laban, Andrew Hsi, John Canny, Marti Hearst
Association for Computational Linguistics (ACL), 2020
What's The Latest? A Question-driven News Chatbot
Philippe Laban, John Canny, Marti Hearst
System Demonstration at ACL, 2020
A framework for a text-centric user interface for navigating complex news stories
Philippe Laban, John Canny, Marti Hearst
Computation + Journalism, 2019
newsLens: building and visualizing long-ranging news stories
Philippe Laban, Marti Hearst
Workshop on Events and Stories in the News, ACL, 2017
Other Work
Abstractive News Summarization via Copying and Transforming
Philippe Laban, John Canny, Marti Hearst
Unpublished, 2019
From Brooklyn Barbers To Movie Stars: Using Introductions To Construct Embeddings Of People
Philippe Laban, John Canny, Marti Hearst
Unpublished, 2018