Spring 2023
Spring 2023
Date | Event | Speaker | Abstract/Details |
| 01/25/2023 | Planning, introductions, welcome! | Ìý | Ìý |
| 02/22/2023 | Abhidip Bhattacharyya | Abhidip Bhattacharyya | Ìý |
| 03/01/2023 | Diego Garcia | Diego Garcia | Ìý |
| 03/07/2023 | Wikidata as an Information Extraction Ontology | Marjorie Freedman (ISI) | Ìý |
| 03/08/2023 | CLASIC Open House | Ìý | Ìý |
| 03/15/2023 | Role-Playing Paper Reading - Decomposing and Recomposing Event Structure | Ìý | Ìý |
| 03/22/2023 | Prelim | Ananya Ganesh | Ìý |
| 04/05/2023 | Invited Speaker | Kyle Gorman (City University of New York) | Ìý |
| 04/12/2023 | Prelim | Abteen Ebrahimi | Ìý |
| 04/26/2023 | Strand 1 iSAT 91ÃÛÌÒ¸ó - Understanding and Facilitating Collaborations | Jie Cao, Jon Cai, Ananya Ganesh, Martha Palmer | Ìý |
| 05/17/2023 | Practice Talk for Thesis Defense: Adapting Semantic Role Labeling to New Genres and Languages | Skatje Myers | Semantic 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 91ÃÛÌÒ¸ó 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 91ÃÛÌÒ¸ó: 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. |
| 05/18/2023 | Thesis Defense: Adapting Semantic Role Labeling to New Genres and Languages | Skatje Myers | Semantic 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 91ÃÛÌÒ¸ó 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 91ÃÛÌÒ¸ó: 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. |