Hi, I am a Ph.D. student (~ June 2017 expected) at Ludwig Maximilian University of Munich, Germany, under the supervision of Prof. Hinrich Schütze. Before coming to Munich, I got MSc degree from Peking University, China in 2013 and BSc degree from Northwestern Polytechnical University, China in 2010.
PhD topic, deep learning in NLP, spans:
In addition, some basic machine learning issues also meet my taste: online learning, domain adaptation, zero/low-shot learning...
1) FLORS: the state-of-the-art online POS tagger in domain adaptation scenario. It performs online representation learning (i.e., domain adaptation is performed by incrementally adapting word representations to the new domain). (EMNLP'2015)
2) Phrase embeddings: the first version in the world. It contains continuous linguistic phrases like "eye disease'' as well as discontinuous phrases like "turn...on'' etc. (ICLR'2013, ACL'2014)
3) Word Meta-Embeddings: A version of word embeddings which were derived by combining several pre-trained word embedding versions, such as word2vec, GloVe, C&W etc. (ACL'2016)
Intern, IBM Watson, Yorktown Heights, NY USA, March -- May 2016.
Honors and Awards: