Prof. Dr. Isbelle Augenstein, University of Copenhagen, Denmark
Date: Thursday, March 5, 2020, 17:15 h
Location: BIN 2.A.01
One of the core challenges in typology is to record properties of languages in a structured way. As a result of manual efforts, typological knowledge bases have emerged, which contains information about languages’ phonological, morphological and syntactic properties; as well as information about language families. Ideally, such typological knowledge bases would provide useful information for multilingual NLP models to learn how to selectively share parameters.
A related area of research suggests a different way of encoding properties of languages, namely to learn language representation vectors directly from text documents.
In this talk, I will analyse and contrast these two ways of encoding linguistic properties, as well as present research on how the two can benefit one another.
Prof. Isabelle Augenstein, Ph.D., is a associate professor at the University of Copenhagen, Department of Computer Science, Denmark, where she heads the Copenhagen NLU research group. Her main research interests are weakly supervised and low-resource learning with applications including information extraction, machine reading and fact checking. In the space of computational typology, she is interested in how information about properties of languages can aid multilingual learning, and has investigated language embeddings as well as automatically populating typological knowledge bases.