Search Challenges in Natural Language Generation with Complex Optimization Objectives

Vera Demberg, Jörg Hoffmann*, David M. Howcroft, Dietrich Klakow, Álvaro Torralba

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

6 Citations (Scopus)


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.

Original languageEnglish
JournalKI - Kunstliche Intelligenz
Issue number1
Pages (from-to)63-69
Number of pages7
Publication statusPublished - 1 Feb 2016
Externally publishedYes


  • Natural language processing
  • Planning
  • Search


Dive into the research topics of 'Search Challenges in Natural Language Generation with Complex Optimization Objectives'. Together they form a unique fingerprint.

Cite this