Dr Alan Akbik

Teaching Machines to Read and Understand Text Data

Research in automatic natural language understanding has made significant strides forward over the past years, and is now poised to deliver a plethora of new technologies for businesses and their customers. A key driving force of this progress is the increasing availability of near-endless amounts of textual data on the Web and elsewhere, as well as recent advances in deep learning. In this talk, I will discuss the topic of text and data mining (TDM) from the point of view of industrial research; I will give an overview of projects we are working on at Zalando Research, and illustrate how TDM technologies are applied to our use cases. In particular, I will focus on our current deep learning research that aims to enable machines to “read and understand” text data, and highlight the potential and limitations of such approaches.


Alan Akbik is a member of the NLP group at Zalando Research, where he is developing advanced text analytics capabilities over large-scale multilingual text data that is often ungrammatical (Web text) and domain-specific. Before this, he was a postdoctoral researcher at IBM Research Almaden in San Jose, California, and before that a research associate at the Technische Universität Berlin. His research lies at the intersection of natural language processing (NLP) and information extraction (IE), with a particular focus on multilingual data and models of crosslingual semantics.