Date(s) - 20/07/2015 - 24/07/2015
University of Aberdeen
The objective of this summer school is to introduce participants to the concepts and research questions in natural language generation (NLG), summarisation and dialogue systems. Although these three areas produce natural language, their distinct communities seldom interact because each community relies on different methods and because the inputs to each kind of system are different. There is, however, considerable overlap in the kinds of problems that need to be considered, from selecting the right content to evaluating the systems. We believe that focusing on the similarities of the different areas can stimulate “cross-pollination” of research. For example, most summarisation techniques could benefit from deeper semantic processing as performed in dialogue systems. Similarly, many NLG systems could benefit from techniques used by dialogue systems to substantially improve the generated output.
The summer school will be primarily aimed at PhD students and early career researchers but more experienced will be admitted to the extent that space permits.
Open Lab sessions, supervised by Dr Yaji Sripada, will focus on building a small NLG system. The system will be implemented in Java so some prior knowledge of the programming language is required. However, we will encourage participants to form small groups or pairs, which should allow non-programmers to participate as well.
Further details of the courses can be found on the website http://nlgsummer.github.io The website will be periodically updated with the latest information. The registration will open at the end of February. The cost of registration will be £200 for students and £300 for others.
SICSA funding is available for a limited number of PhD students studying Computer Science at SICSA universities. Funding will cover the cost of registration only. Eligible applicants can apply for SICSA funding by emailing the following information to email@example.com: student name, aliation, PhD topic, supervisor name, one paragraph indicating why they feel that this workshop is relevant to their research, and any previous publications / papers in preparation.
Kees van Deemter
Contact us at: firstname.lastname@example.org