Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation

Simeon Schüz, Sina Zarrieß


Abstract
The shift to neural models in Referring Expression Generation (REG) has enabled more natural set-ups, but at the cost of interpretability. We argue that integrating pragmatic reasoning into the inference of context-agnostic generation models could reconcile traits of traditional and neural REG, as this offers a separation between context-independent, literal information and pragmatic adaptation to context. With this in mind, we apply existing decoding strategies from discriminative image captioning to REG and evaluate them in terms of pragmatic informativity, likelihood to ground-truth annotations and linguistic diversity. Our results show general effectiveness, but a relatively small gain in informativity, raising important questions for REG in general.
Anthology ID:
2021.reinact-1.7
Volume:
Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)
Month:
October
Year:
2021
Address:
Gothenburg, Sweden
Editors:
Christine Howes, Simon Dobnik, Ellen Breitholtz, Stergios Chatzikyriakidis
Venue:
ReInAct
SIG:
SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
47–52
Language:
URL:
https://aclanthology.org/2021.reinact-1.7
DOI:
Bibkey:
Cite (ACL):
Simeon Schüz and Sina Zarrieß. 2021. Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation. In Proceedings of the Reasoning and Interaction Conference (ReInAct 2021), pages 47–52, Gothenburg, Sweden. Association for Computational Linguistics.
Cite (Informal):
Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation (Schüz & Zarrieß, ReInAct 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.reinact-1.7.pdf
Data
MS COCORefCOCO