Personal Information

Name
Yang Gao
Position
Postdoctoral Researcher
Affiliation
UKP-TUDA
E-Mail
gao(at)ukp.informatik.tu-darmstadt.de
Phone
+49 (6151) 16 - 21677
Fax
+49 (6151) 16 - 25295
Office
S2|02 B106
Address

TU Darmstadt - FB 20
Hochschulstraße 10
64289 Darmstadt
Germany 

Research Interests

I am interested in applying reinforcement learning (RL) algorithms in natural language processing (NLP) tasks. RL is famous for its sequential decision-making capabilities, and many NLP tasks can actually be formulated as sequential decision-making problems, e.g. dependency parsing, document summarisation and dialogue generation. I am particularly interested in applying RL in interactive NLP tasks.

Biographical Information

I joined the UKP group in June 2017 as a postdoc researcher. Before that, I worked as an assistant professor in Institute of Software, Chinese Academy of Sciences, from Sep 2015 to Jun 2017, working on text mining and argumentation mining. I obtained my PhD degree from Dep. of Computing, Imperial College London, in Apr 2015, under the supervision of Prof. Francesca Toni, and my thesis is about using argumentation-based domain knowledge to speed up reinforcement learning algorithms. I hold a Bachalor of Engineering degress from Northwestern Polytechnical University in China.  

A A A | Drucken Print | Impressum Impressum | Sitemap Sitemap | Suche Search | Kontakt Contact | Webseitenanalyse: Mehr Informationen
zum Seitenanfangzum Seitenanfang