@inproceedings{schuz-zarriess-2021-decoupling,
title = "Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation",
author = {Sch{\"u}z, Simeon and
Zarrie{\ss}, Sina},
editor = "Howes, Christine and
Dobnik, Simon and
Breitholtz, Ellen and
Chatzikyriakidis, Stergios",
booktitle = "Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)",
month = oct,
year = "2021",
address = "Gothenburg, Sweden",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.reinact-1.7",
pages = "47--52",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schuz-zarriess-2021-decoupling">
<titleInfo>
<title>Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Simeon</namePart>
<namePart type="family">Schüz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sina</namePart>
<namePart type="family">Zarrieß</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christine</namePart>
<namePart type="family">Howes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Dobnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ellen</namePart>
<namePart type="family">Breitholtz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stergios</namePart>
<namePart type="family">Chatzikyriakidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gothenburg, Sweden</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">schuz-zarriess-2021-decoupling</identifier>
<location>
<url>https://aclanthology.org/2021.reinact-1.7</url>
</location>
<part>
<date>2021-10</date>
<extent unit="page">
<start>47</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation
%A Schüz, Simeon
%A Zarrieß, Sina
%Y Howes, Christine
%Y Dobnik, Simon
%Y Breitholtz, Ellen
%Y Chatzikyriakidis, Stergios
%S Proceedings of the Reasoning and Interaction Conference (ReInAct 2021)
%D 2021
%8 October
%I Association for Computational Linguistics
%C Gothenburg, Sweden
%F schuz-zarriess-2021-decoupling
%X 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.
%U https://aclanthology.org/2021.reinact-1.7
%P 47-52
Markdown (Informal)
[Decoupling Pragmatics: Discriminative Decoding for Referring Expression Generation](https://aclanthology.org/2021.reinact-1.7) (Schüz & Zarrieß, ReInAct 2021)
ACL