• Seminars & Events
  • Latest
  • Archive
  • RSS Feed

Back

24 April 2008

Generation as planning

Location: Room 308, Maths & Computing Building
Time: 12.00-13.45
Speaker(s): Alexander Koller, University of Edinburgh

The problem of natural language generation is intimately related to AI planning on many levels. In both problems, the computer has to search for a sequence of actions that combine in appropriate ways to achieve a given goal; in the case of generation, these actions may correspond to uttering speech acts, sentences, or individual words. This has been recognized in the literature for several decades, but we are currently experiencing a revival of interest in exploring this connection, which has been sparked especially by the recent advances in making planners efficient. In my talk, I will first show how sentence generation can be translated into a planning problem. This has the advantage that the (somewhat artificial) separation of sentence generation into microplanning and surface realization can be overcome, in a way that's similar to Matthew Stone's SPUD system. Furthermore, each plan action captures the complete grammatical, semantic, and pragmatic preconditions and effects of uttering a single word. I will then present a recent proposal for a shared task for the generation community, in which the system must generate instructions in a virtual environment, discuss some problems that arise in this application, and propose some ideas on how these can be tackled using a planning approach. Alexander Koller received his PhD from Saarland University in Saarbruecken, Germany in 2004. He holds a two-year DFG Research Fellowship; after spending the first year at Columbia University, he is now at the University of Edinburgh. The focus of his current research is the development of efficient algorithms for natural language generation, in particular by applying planning algorithms. He also works on computational semantics and formal languages.


Save to your Calendar

Contact: mailto: r.power@open.ac.uk