At this week’s lab meeting, Andrew Piper will give a talk titled “Narrative Theory and Computational Narrative Understanding.”
- Tuesday, December 7, 15:00–16:00 (Montreal time, UTC-5).
- Meetings are via Zoom. If you would like to attend the talk but have not yet signed up for the MCQLL meetings this semester, please send an email to firstname.lastname@example.org.
Narration is a universal human practice that serves as a key site of education, collective memory, fostering social belief systems, and furthering human creativity. Recent studies in economics (Shiller, 2020), climate science (Bushell et al., 2017), political polarization (Kubin et al., 2021), and mental health (Adler et al., 2016) suggest an emerging interdisciplinary consensus that narrative is a central concept for understanding human behavior and beliefs. Given this importance of narrative, a growing body of work in NLP has begun focusing on the problem of narrative understanding. And yet much of this work remains largely divorced from the rich theoretical tradition of narratology that has been developed over the past half century. This talk is based on our recent EMNLP paper (Piper et al 2021) and aims to provide a unifying theoretical framework for the computational study of narrative. By providing the NLP community with a more coherent theoretical foundation, our goal is to identify new salient high-level problems of narrative understanding for the NLP community to address as they relate to questions of social conflict, creative industries, and social and mental well-being. My talk will walk us through: a) a basic theoretical framework for narrative understanding; b) large scale challenges for the field and their social relevance; and c) some examples of recent work in my lab on computational narrative understanding.
Links to papers:
Piper et al, “Narrative Theory for Computational Narrative Understanding”
Piper et al, “Detecting Narrativity Across Long Time Scales”