Spring 2023

Date

Event

Speaker

Abstract/Details

01/25/2023Planning, introductions, welcome!ÌýÌý
02/22/2023Abhidip BhattacharyyaAbhidip BhattacharyyaÌý
03/01/2023Diego GarciaDiego GarciaÌý
03/07/2023Wikidata as an Information Extraction OntologyMarjorie Freedman (ISI)Ìý
03/08/2023CLASIC Open HouseÌýÌý
03/15/2023Role-Playing Paper Reading - Decomposing and Recomposing Event StructureÌýÌý
03/22/2023PrelimAnanya GaneshÌý
04/05/2023Invited SpeakerKyle Gorman (City University of New York)Ìý
04/12/2023PrelimAbteen EbrahimiÌý
04/26/2023Strand 1 iSAT Research - Understanding and Facilitating CollaborationsJie Cao, Jon Cai, Ananya Ganesh, Martha PalmerÌý
05/17/2023Practice Talk for Thesis Defense: Adapting Semantic Role Labeling to New Genres and LanguagesSkatje MyersSemantic role labeling (SRL) is the identification of semantic predicates and their participants within a sentence, which is vital for deeper natural language understanding. Current SRL models require annotated text for training, but this is unavailable in many domains and languages. We explore two different ways of reducing the annotation required to produce effective SRL models: 1) using active learning to target only the most informative training instances and 2) leveraging parallel sentences to project SRL annotations from one language into the target language.
05/18/2023Thesis Defense: Adapting Semantic Role Labeling to New Genres and LanguagesSkatje MyersSemantic role labeling (SRL) is the identification of semantic predicates and their participants within a sentence, which is vital for deeper natural language understanding. Current SRL models require annotated text for training, but this is unavailable in many domains and languages. We explore two different ways of reducing the annotation required to produce effective SRL models: 1) using active learning to target only the most informative training instances and 2) leveraging parallel sentences to project SRL annotations from one language into the target language.