First workshop on Transcript Understanding

17 October, 2022

Location: Gyeongju, Republic of Korea

Fei Liu

Associate Professor
Department of Computer Science
Emory University


Title

TOWARD AUTOMATIC TRANSCRIPT SUMMARIZATION: CHALLENGES AND OPPORTUNITIES

Abstract

The exploding reach and power of audio and video, combined with accurate captioning, is broadening access to large collections of transcripts. Automatic transcript summarization aims to produce textual summaries from transcripts of audio and video recordings. Whether one needs to share the minutes of a meeting or quickly take notes of a livestream, using a transcript summarization tool is a convenient way to outsource the otherwise labor intensive task of turning voice recordings into textual summaries. Though practitioners are eager to summarize transcripts of various sorts, they cannot deal with the complexities of spoken language. In this talk, I will discuss our recent work on generating podcast summaries from automatic transcripts. Our summarizer learns to produce an abstractive summary while grounding summary segments in the original audio. Grounding allows users to interpret and place into context any system-generated summary, thus reducing the barriers to deploy summarization technology. I will conclude the talk by discussing challenges and opportunities in automatic transcript summarization and pointing to avenues for future research.

Short biography

Dr. Fei Liu is an associate professor of Computer Science at Emory University, where she co-directs the Natural Language Processing Group. Her research areas are natural language processing and deep learning, with a special emphasis on automatic summarization. Her research aims to generate textual summaries from a massive amount of data to combat information overload. Building on recent advances in deep learning, Dr. Liu's research explores both extractive and abstractive approaches to generate informative, succinct, and accurate summaries.

Dr. Liu was a postdoctoral fellow at Carnegie Mellon University, member of Noah's ARK. She worked as a senior scientist at Bosch Research, Palo Alto, California, one of the largest German companies building intelligent car systems and home appliances. Liu received her Ph.D. in Computer Science from the University of Texas at Dallas in 2011, supported by Erik Jonsson Distinguished Research Fellowship. She obtained her Bachelor's and Master's degrees in Computer Science from Fudan University. Dr. Liu has published 70+ peer-reviewed papers in leading conferences and journals. She regularly serves on program committees of major international conferences. Liu was selected for the 2015 "MIT Rising Stars in EECS" program. Her work was nominated as Best Paper Award Finalist at WWW 2016 and Area Chair Favorite Paper at COLING 2018.

Contact us: vietl@uoregon.edu