Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning

Sina Zarrieß, Hendrik Buschmeier, Ting Han, Simeon Schüz


Abstract
Recent work has adopted models of pragmatic reasoning for the generation of informative language in, e.g., image captioning. We propose a simple but highly effective relaxation of fully rational decoding, based on an existing incremental and character-level approach to pragmatically informative neural image captioning. We implement a mixed, ‘fast’ and ‘slow’, speaker that applies pragmatic reasoning occasionally (only word-initially), while unrolling the language model. In our evaluation, we find that increased informativeness through pragmatic decoding generally lowers quality and, somewhat counter-intuitively, increases repetitiveness in captions. Our mixed speaker, however, achieves a good balance between quality and informativeness.
Anthology ID:
2021.inlg-1.41
Volume:
Proceedings of the 14th International Conference on Natural Language Generation
Month:
August
Year:
2021
Address:
Aberdeen, Scotland, UK
Editors:
Anya Belz, Angela Fan, Ehud Reiter, Yaji Sripada
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
371–376
Language:
URL:
https://aclanthology.org/2021.inlg-1.41
DOI:
10.18653/v1/2021.inlg-1.41
Bibkey:
Cite (ACL):
Sina Zarrieß, Hendrik Buschmeier, Ting Han, and Simeon Schüz. 2021. Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning. In Proceedings of the 14th International Conference on Natural Language Generation, pages 371–376, Aberdeen, Scotland, UK. Association for Computational Linguistics.
Cite (Informal):
Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning (Zarrieß et al., INLG 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.inlg-1.41.pdf
Data
MS COCO