Talk Title: Shallow vs Deep Models for Dialect Identification

Abstract: Following our participation in the VarDial evaluation campaigns on dialect identification since 2016, we have witnessed a head-to-head comparison of shallow and deep learning models over several years. Interestingly, it seems that, for the dialect identification task, deep learning models are seriously challenged by shallow methods based on low-level features, e.g. character n-grams. In this talk, we will review a series of successful dialect identification approaches, either based on engineered or deep features, discussing the benefits and the downsides of each method. At the end, we will present some takeaways for future research on dialect identification.

Short Bio: Radu Tudor Ionescu is Professor at the University of Bucharest, Romania. He completed his PhD at the University of Bucharest in 2013. He received the 2014 Award for Outstanding Doctoral Research in the field of Computer Science from the Romanian Ad Astra Association. His research interests include machine learning, computer vision, image processing, medical imaging, computational linguistics and text mining. He published over 100 articles at international peer-reviewed conferences and journals, and a research monograph with Springer. He received the "Caianiello Best Young Paper Award" at ICIAP 2013 for the paper entitled "Kernels for Visual Words Histograms". Radu also received the "2017 Young Researchers in Science and Engineering" Prize for young Romanian researchers and the "Danubius Young Scientist Award 2018 for Romania" by the Austrian Federal Ministry of Education, Science and Research and by the Institute for the Danube Region and Central Europe. Together with other co-authors, he obtained good rankings at several international competitions: 4th place in the Facial Expression Recognition Challenge of WREPL 2013, 3rd place in the NLI Shared Task of BEA-8 2013, 2nd place in the ADI Shared Task of VarDial 2016, 1st place in the ADI Shared Task of VarDial 2017, 1st place in the NLI Shared Task of BEA-12 2017, 1st place in the ADI Shared Task of VarDial 2018.