Search Challenges in Natural Language Generation with Complex Optimization Objectives
| dc.contributor.author | Demberg, Vera | |
| dc.contributor.author | Hoffmann, Jörg | |
| dc.contributor.author | Howcroft, David M. | |
| dc.contributor.author | Klakow, Dietrich | |
| dc.contributor.author | Torralba, Álvaro | |
| dc.date.accessioned | 2018-01-08T09:22:58Z | |
| dc.date.available | 2018-01-08T09:22:58Z | |
| dc.date.issued | 2016 | |
| dc.description.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. | |
| dc.identifier.pissn | 1610-1987 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/11503 | |
| dc.publisher | Springer | |
| dc.relation.ispartof | KI - Künstliche Intelligenz: Vol. 30, No. 1 | |
| dc.relation.ispartofseries | KI - Künstliche Intelligenz | |
| dc.subject | Natural language processing | |
| dc.subject | Planning | |
| dc.subject | Search | |
| dc.title | Search Challenges in Natural Language Generation with Complex Optimization Objectives | |
| dc.type | Text/Journal Article | |
| gi.citation.endPage | 69 | |
| gi.citation.startPage | 63 |