Dependency Parsing and Information Extraction in Low-Resource Scenarios

• Event: Seminar
• Lecturer: Barbara Plank from IT University of Copenhagen
• Date: 20 April 2022
• Duration: 2 hours
• Venue: Gothenburg and Online

Abstract:

“The recent success of Natural Language Processing is driven by advances in modelling paired with strong language model encoders. However, for many application scenarios like low-resource languages and specific application domains we do not have access to labeled resources and even unlabelled data might be scarce. In this talk, I will present some of our recent work on how to transfer models to low-resource languages and language variants with the use of incidental (or fortuitous) learning signals such as genre paired with data selection for cross-lingual dependency parsing. I will further discuss some insights from our recent study on segment embeddings in multilingual BERT models, and on-going work on information extraction for computational job market analysis.”