@inproceedings{zarriess-etal-2021-decoding,
title = "Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning",
author = {Zarrie{\ss}, Sina and
Buschmeier, Hendrik and
Han, Ting and
Sch{\"u}z, Simeon},
editor = "Belz, Anya and
Fan, Angela and
Reiter, Ehud and
Sripada, Yaji",
booktitle = "Proceedings of the 14th International Conference on Natural Language Generation",
month = aug,
year = "2021",
address = "Aberdeen, Scotland, UK",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.inlg-1.41",
doi = "10.18653/v1/2021.inlg-1.41",
pages = "371--376",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zarriess-etal-2021-decoding">
<titleInfo>
<title>Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hendrik</namePart>
<namePart type="family">Buschmeier</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simeon</namePart>
<namePart type="family">Schüz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 14th International Conference on Natural Language Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Belz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angela</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehud</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaji</namePart>
<namePart type="family">Sripada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Aberdeen, Scotland, UK</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">zarriess-etal-2021-decoding</identifier>
<identifier type="doi">10.18653/v1/2021.inlg-1.41</identifier>
<location>
<url>https://aclanthology.org/2021.inlg-1.41</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>371</start>
<end>376</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning
%A Zarrieß, Sina
%A Buschmeier, Hendrik
%A Han, Ting
%A Schüz, Simeon
%Y Belz, Anya
%Y Fan, Angela
%Y Reiter, Ehud
%Y Sripada, Yaji
%S Proceedings of the 14th International Conference on Natural Language Generation
%D 2021
%8 August
%I Association for Computational Linguistics
%C Aberdeen, Scotland, UK
%F zarriess-etal-2021-decoding
%X 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.
%R 10.18653/v1/2021.inlg-1.41
%U https://aclanthology.org/2021.inlg-1.41
%U https://doi.org/10.18653/v1/2021.inlg-1.41
%P 371-376
Markdown (Informal)
[Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning](https://aclanthology.org/2021.inlg-1.41) (Zarrieß et al., INLG 2021)
ACL