Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation

Schüz S, Zarrieß S (2021)
In: Proceedings of the Reasoning and Interaction Conference (ReInAct 2021). Gothenburg, Sweden: Association for Computational Linguistics: 47-52.

Konferenzbeitrag | Englisch
 
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Einrichtung
Abstract / Bemerkung
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.
Erscheinungsjahr
2021
Titel des Konferenzbandes
Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)
Seite(n)
47-52
Konferenz
Reasoning and Interaction
Konferenzort
Gothenburg, Sweden
Konferenzdatum
2021-10-04 – 2021-10-06
Page URI
https://pub.uni-bielefeld.de/record/2958059

Zitieren

Schüz S, Zarrieß S. Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation. In: Proceedings of the Reasoning and Interaction Conference (ReInAct 2021). Gothenburg, Sweden: Association for Computational Linguistics; 2021: 47-52.
Schüz, S., & Zarrieß, S. (2021). Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation. Proceedings of the Reasoning and Interaction Conference (ReInAct 2021), 47-52. Gothenburg, Sweden: Association for Computational Linguistics.
Schüz, S., and Zarrieß, S. (2021). “Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation” in Proceedings of the Reasoning and Interaction Conference (ReInAct 2021) (Gothenburg, Sweden: Association for Computational Linguistics), 47-52.
Schüz, S., & Zarrieß, S., 2021. Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation. In Proceedings of the Reasoning and Interaction Conference (ReInAct 2021). Gothenburg, Sweden: Association for Computational Linguistics, pp. 47-52.
S. Schüz and S. Zarrieß, “Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation”, Proceedings of the Reasoning and Interaction Conference (ReInAct 2021), Gothenburg, Sweden: Association for Computational Linguistics, 2021, pp.47-52.
Schüz, S., Zarrieß, S.: Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation. Proceedings of the Reasoning and Interaction Conference (ReInAct 2021). p. 47-52. Association for Computational Linguistics, Gothenburg, Sweden (2021).
Schüz, Simeon, and Zarrieß, Sina. “Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation”. Proceedings of the Reasoning and Interaction Conference (ReInAct 2021). Gothenburg, Sweden: Association for Computational Linguistics, 2021. 47-52.
Link(s) zu Volltext(en)
Access Level
OA Open Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar