Dr. Mark Finlayson of the Computer Science and Artificial Intelligence Laboratory at MIT will speak on "Learning Narrative Structure from Semantically Annotated Text."
Narrative structure is an ubiquitous and intriguing phenomenon. It is
found across cultures, domains, and tasks, helping us understand the
higher-level meaning of texts and effectively use stories for a variety
of purposes. Understanding and modeling narrative structure is an anvil
for forging new artificial intelligence and machine learning techniques,
and is a window into abstraction and conceptual learning as well as into
culture and its influence on cognition. I describe my research program
for computationally modeling and extracting narrative structure from
natural language texts. First, I will present Analogical Story Merging
(ASM), a new machine learning algorithm for extracting plot patterns
from sets of stories. I demonstrate, for the first time, the learning of
a theory of narrative structure from text: ASM can learn a substantive
portion of Vladimir Propp's influential theory of the structure of
folktale plots. Second, I will discuss the Story Workbench, a
general-purpose text annotation tool for supports the semi-automatic
markup of over twenty different syntactic and semantic representations
that I have used to assemble the largest and most deeply-annotated
narrative corpus to date. Third, I will illustrate some
hot-off-the-press work: (a) recent experiments demonstrating for
the first time that highly-trained annotators can reliably capture
explicit narrative structures from text; and (b) new applications of
my work in the health domain, under a newly funded NIH R01. Finally,
I will outline my future research plans, which involve automatically
processing very large corpora; applying my techniques to new domains
such as business, finance, law, and medicine; cognitive psychology
experiments to "close the loop" and determine the cognitive reality of
identified patterns; and defining a new field of study around the topic
of "cultural genomics".
Dr. Mark Finlayson is a Research Scientist at the Computer Science
and Artificial Intelligence Laboratory at MIT. His research focuses on
representing, extracting, and using higher-order semantic patterns in
natural language. He received the B.S.E in Electrical Engineering from
the University of Michigan in 1998, the M.S. in Electrical Engineering
from MIT in 2001, and the Ph.D. in Computer Science from MIT in 2012.
He is general chair of the Computational Models of Workshop series, now
in its fifth year.
Events are free and open to the public unless otherwise noted.