Search Challenges in Natural Language Generation with Complex Optimization Objectives. Demberg, V.; Hoffmann, J.; Howcroft, D. M.; Klakow, D.; and Torralba, Á. In
abstract   bibtex   
Automatic natural language generation (NLG) is a difficult problem already when merely trying to come up with natural-sounding utterances. Ubiquituous applications, in particular companion technologies, pose the additional challenge of flexible adaptation to a user or a situation. This requires optimizing complex objectives such as information density, in combinatorial search spaces described using declarative input languages. We believe that AI search and planning is a natural match for these problems, and could substantially contribute to solving them effectively. We illustrate this using a concrete example NLG framework, give a summary of the relevant optimization objectives, and provide an initial list of research challenges.
@InProceedings{spark16-10,
  author =   {Vera Demberg and Joerg Hoffmann and David M. Howcroft and Dietrich Klakow and Álvaro Torralba},
  title =    {Search Challenges in Natural Language Generation with Complex Optimization Objectives},
  abstract = {Automatic natural language generation (NLG) is a difficult problem 
already when merely trying to come up with natural-sounding 
utterances. Ubiquituous applications, in particular companion 
technologies, pose the additional challenge of flexible adaptation to 
a user or a situation. This requires optimizing complex objectives 
such as information density, in combinatorial search spaces described 
using declarative input languages. We believe that AI search and 
planning is a natural match for these problems, and could 
substantially contribute to solving them effectively. We illustrate 
this using a concrete example NLG framework, give a summary of the 
relevant optimization objectives, and provide an initial list of 
research challenges.},
  keywords = {Natural language processing, Search, Planning}
}
Downloads: 0