Events
ML+ X Seminar
New Challenges in Text Simplification
Jessy Li, Assistant Professor, Department of Linguistics, The University of Texas at Austin
-The University of Texas at Austin
GDC 6.302
United States
Abstract
Text simplification aims to help audiences read and understand a piece of text through lexical, syntactic, and discourse modifications, while remaining faithful to its central idea and meaning. Thanks to large-scale parallel corpora derived from Wikipedia and News, modern text generation models can be trained to transform original, more complex sentences into fluent, simplified versions. In this talk, I present a series of new frontiers within this existing paradigm and beyond. First, we discuss simplification in new domains, and propose the challenging task of simplifying highly technical medical texts. Second, we present the first data-driven study of inserting elaborations and explanations during simplification, and illustrate the richness and complexities of this phenomenon. Finally, we discuss our analysis highlighting the unique characteristics of factual accuracy in the context of simplification.
Text simplification aims to help audiences read and understand a piece of text through lexical, syntactic, and discourse modifications, while remaining faithful to its central idea and meaning. Thanks to large-scale parallel corpora derived from Wikipedia and News, modern text generation models can be trained to transform original, more complex sentences into fluent, simplified versions. In this talk, I present a series of new frontiers within this existing paradigm and beyond. First, we discuss simplification in new domains, and propose the challenging task of simplifying highly technical medical texts. Second, we present the first data-driven study of inserting elaborations and explanations during simplification, and illustrate the richness and complexities of this phenomenon. Finally, we discuss our analysis highlighting the unique characteristics of factual accuracy in the context of simplification.
Speaker Bio
Jessy Li is an assistant professor in the Department of Linguistics at UT Austin where she works on in computational linguistics and natural language processing. Her work focuses on discourse processing, text generation, and language in social contexts. She received her Ph.D. in 2017 from the University of Pennsylvania. She received an ACM SIGSOFT Distinguished Paper Award at FSE 2019, an Area Chair Favorite paper at COLING 2018, and a Best Paper nomination at SIGDIAL 2016.
Jessy Li is an assistant professor in the Department of Linguistics at UT Austin where she works on in computational linguistics and natural language processing. Her work focuses on discourse processing, text generation, and language in social contexts. She received her Ph.D. in 2017 from the University of Pennsylvania. She received an ACM SIGSOFT Distinguished Paper Award at FSE 2019, an Area Chair Favorite paper at COLING 2018, and a Best Paper nomination at SIGDIAL 2016.