CIIR Talk Series
Title: Listening to Our Listeners: Podcast Content Understanding for Search and Recommendation
Abstract: Podcasts are increasing in popularity and are seeing world-wide growth. They run the gamut of styles and genres, are multi-modal, and represent a large time commitment for listeners. To help our listeners, we need good representations of the content of podcasts. I'll give an overview of our recent research into user engagement with podcasts and techniques to facilitate podcast access, including summarization and search, and sketch some directions for future research.
Bio: Rosie Jones is Director of Research in Language Technologies at Spotify, based in Boston, MA, USA, where she leads a team of research scientists working on language technologies for music and podcast understanding and recommendation. Her team is leading the TREC evaluation on podcast summarization and search, and has released a 100k corpus of podcast descriptions, transcripts and audio to accompany the TREC challenge. She has also worked at Microsoft, in the New England Research and Development Center (NERD), on conversational understanding, and as Director of Data Science at MediaMath, where she led a team conducting research on large-scale machine-learned models for display advertising. She started her career as a scientist at Yahoo! Labs, working on search and sponsored search. Rosie has a PhD from the Language Technologies Institute at Carnegie Mellon University, and her Bachelor of Science from the University of Sydney. She also holds a role as Honorary Professor at RMIT University in Melbourne, Australia. Her academic service includes PC Co-Chair for SIGIR 2021, as well as past reviewing and meta-reviewing for ACL, IJCAI, WWW, WSDM and KDD.
To attend this talk via Zoom, click here. Participants will need a passcode to attend this event. If you need the passcode for this series, please see the event advertisement on the seminars email list or reach out to Alex Taubman. For any questions about this event with the Center for Intelligent Information Retrieval, please contact Jean Joyce.