A7: Controlling Information Density in Discourse Generation

Project A7 aims to develop a system which generates effective technical instruction videos for the computer game “Minecraft”. This system will implement a rational speaker who trades off communicative success (being understood by the listener) against succinctness, in particular with respect to the listener’s domain knowledge and the division of labor between language and video. To find near-optimal communicative choice efficiently enough for interactive use, the project will advance heuristic search methods within and across the generation of individual sentences.

Publications

2020

Höller, Daniel; Bercher, Pascal; Behnke, Gregor

Delete- and Ordering-Relaxation Heuristics for HTN Planning Inproceedings Forthcoming

Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI), Yokohama, Japan, Forthcoming.

BibTeX

Wichlacz, Julia; Höller, Daniel; Torralba, Álvaro; Hoffmann, Jörg

Applying Monte-Carlo Tree Search in HTN Planning Inproceedings

Proceedings of the 13th International Symposium on Combinatorial Search (SoCS), pp. 82-90, AAAI Press, Vienna, Austria, 2020.

Abstract | Links | BibTeX

2019

Köhn, Arne; Koller, Alexander

Talking about what is not there: Generating indefinite referring expressions in Minecraft Inproceedings

Proceedings of the 12th International Conference on Natural Language Generation, pp. 1-10, Association for Computational Linguistics, Tokyo, Japan, 2019.

Abstract | Links | BibTeX

Wichlacz, Julia; Torralba, Álvaro; Hoffmann, Jörg

Construction-Planning Models in Minecraft Inproceedings

Proceedings of the 2nd Workshop on Hierarchical Planning at ICAPS 2019, pp. 1-5, 2019.

Abstract | Links | BibTeX

Jörg Hoffmann

PI

Mail
Website

Alexander Koller

PI

Mail
Website

Julia Wichlacz

PhD

Mail

Arne Köhn

Postdoc

Mail
Website