Research in natural language processing (NLP) has seen many advances over the recent years, from word embeddings to pretrained language models. However, most of these approaches rely on large labelled datasets, which has constrained their success to languages where such data is plentiful. In this talk, I will give an overview of approaches that transfer knowledge across languages and enable us to scale NLP models to more of the world's 7,000 languages. I will cover the spectrum of recent cross-lingual transfer approaches, from word embeddings to deep pretrained models. The talk will conclude with a discussion of the cutting-edge of learning such representations, their limitations, and future directions.
On his webpage ruder.io, which is also a well-known Machine Learning blog, Sebastian writes: I'm a research scientist at DeepMind, London. I completed my PhD in Natural Language Processing and Deep Learning at the Insight Research Centre for Data Analytics, while working as a research scientist at Dublin-based text analytics startup AYLIEN. Previously, I've studied Computational Linguistics at the University of Heidelberg, Germany and at Trinity College, Dublin. During my studies, I've worked with Microsoft, IBM's Extreme Blue, Google Summer of Code, and SAP, among others. I'm interested in transfer learning for NLP and making ML and NLP more accessible.
The event will take place on Thursday, 6 February, 2020 at 6:15pm at the Seminarraum in Gästehaus of University Heidelberg, Im Neuenheimer Feld 370. Drinks and Pizza will be provided, courtesy of the Division of Medical Image Computing at DKFZ. Kindly help us plan ahead by registering for the event on our meetup page.