学术报告通知

报告人：   香港城市大学博士生宋彦
时  间：   2013年7月18日（周四）晚7:00~8:00
地  点：   南京理工大学经济管理学院617会议室

题  目：   Exploiting Source Domain Data for Domain Adaptation
摘  要：

A critical limitation of the current domain adaptation method is that it usually requires labeled data from a target domain and very often such data is lacking. Smartly using existing training (source domain) data to tackle such problem is meaningful and practical to real applications. One solution is to use training data selection to divide the source domain training data into two parts, pseudo target data (the selected part) and source data (the unselected part), and then apply feature augmentation on the two parts of the training data. This approach has two advantages: first, feature augmentation can be applied even when there is no labeled data from the target domain; second, the approach can take advantage of all the training data including the part that is not selected by training data selection. This approach is theoretically applicable to every supervised learning task. Results from some NLP tasks confirm its validity and effectiveness.

报告人简历：

Yan Song is a PhD candidate in the Department of Chinese, Translation and Linguistics at City University of Hong Kong. He was a visiting researcher at Microsoft Research Asia in 2010 and a visiting researcher at the University of Washington from 2011 to 2012. His research interests include machine translation and transliteration, Chinese language processing, machine learning for NLP with special focus on domain adaptation.