Being data-driven is not enough: Revisiting interactive instruction giving as a challenge for NLG

Sina Zarrieß, David Schlangen


Abstract
Modeling traditional NLG tasks with data-driven techniques has been a major focus of research in NLG in the past decade. We argue that existing modeling techniques are mostly tailored to textual data and are not sufficient to make NLG technology meet the requirements of agents which target fluid interaction and collaboration in the real world. We revisit interactive instruction giving as a challenge for datadriven NLG and, based on insights from previous GIVE challenges, propose that instruction giving should be addressed in a setting that involves visual grounding and spoken language. These basic design decisions will require NLG frameworks that are capable of monitoring their environment as well as timing and revising their verbal output. We believe that these are core capabilities for making NLG technology transferrable to interactive systems.
Anthology ID:
W18-6906
Volume:
Proceedings of the Workshop on NLG for Human–Robot Interaction
Month:
November
Year:
2018
Address:
Tilburg, The Netherlands
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
27–31
Language:
URL:
https://aclanthology.org/W18-6906
DOI:
10.18653/v1/W18-6906
Bibkey:
Cite (ACL):
Sina Zarrieß and David Schlangen. 2018. Being data-driven is not enough: Revisiting interactive instruction giving as a challenge for NLG. In Proceedings of the Workshop on NLG for Human–Robot Interaction, pages 27–31, Tilburg, The Netherlands. Association for Computational Linguistics.
Cite (Informal):
Being data-driven is not enough: Revisiting interactive instruction giving as a challenge for NLG (Zarrieß & Schlangen, INLG 2018)
Copy Citation:
PDF:
https://preview.aclanthology.org/starsem-semeval-split/W18-6906.pdf