Embedding Language and Space
演讲者： Professor Tim Baldwin (The University of Melbourne)
In this talk, I will present recent work on the dual tasks of Twitter geolocation prediction (predicting the location of a user given tweets by them) and computational dialectology (esp. the tasks of predicting the geographic distribution of terms, or ranking terms for dialectal specificity to a given location) based on representation learning. Time permitting, I will also present work on topic-biased language models, where the model jointly predicts the topic bias of a particular passage of text, and biases its language model predictions accordingly.
Tim Baldwin is a Professor in the Department of Computing and Information Systems, The University of Melbourne, and Associate Dean (Research Training) within the Melbourne School of Engineering. He is also Director of the recently-awarded ARC Centre for Cognitive Computing in Medical Technologies, in partnership with IBM Research. He has previously held visiting positions at Cambridge University, University of Washington, University of Tokyo, Saarland University, NTT Communication Science Laboratories, and National Institute of Informatics. His research interests include text mining of social media, computational lexical semantics, deep learning, and web mining.
Tim completed a BSc(CS/Maths) and BA(Linguistics/Japanese) at The University of Melbourne in 1995, and an MEng(CS) and PhD(CS) at the Tokyo Institute of Technology in 1998 and 2001, respectively. Prior to joining The University of Melbourne in 2004, he was a Senior Research Engineer at the Center for the Study of Language and Information, Stanford University (2001-2004). He is the author of well over 300 peer-reviewed publications across diverse topics in natural language processing, and the most highly published NLP author of all time according to the ACL Anthology.