@inproceedings{ellison-same-2024-experimental,
title = "Experimental versus In-Corpus Variation in Referring Expression Choice",
author = "Ellison, T. Mark and
Same, Fahime",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.597",
pages = "6838--6848",
abstract = "In this paper, we compare the results of three studies. The first explored feature-conditioned distributions of referring expression (RE) forms in the original corpus from which the contexts were taken. The second is a crowdsourcing study in which we asked participants to express entities within a pre-existing context, given fully specified referents. The third study replicates the crowdsourcing experiment using Large Language Models (LLMs). We evaluate how well the corpus itself can model the variation found when multiple informants (either human participants or LLMs) choose REs in the same contexts. We measure the similarity of the conditional distributions of form categories using the Jensen-Shannon Divergence metric and Description Length metric. We find that the experimental methodology introduces substantial noise, but by taking this noise into account, we can model the variation captured from the corpus and RE form choices made during experiments. Furthermore, we compared the three conditional distributions over the corpus, the human experimental results, and the GPT models. Against our expectations, the divergence is greatest between the corpus and the GPT model.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ellison-same-2024-experimental">
<titleInfo>
<title>Experimental versus In-Corpus Variation in Referring Expression Choice</title>
</titleInfo>
<name type="personal">
<namePart type="given">T</namePart>
<namePart type="given">Mark</namePart>
<namePart type="family">Ellison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fahime</namePart>
<namePart type="family">Same</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we compare the results of three studies. The first explored feature-conditioned distributions of referring expression (RE) forms in the original corpus from which the contexts were taken. The second is a crowdsourcing study in which we asked participants to express entities within a pre-existing context, given fully specified referents. The third study replicates the crowdsourcing experiment using Large Language Models (LLMs). We evaluate how well the corpus itself can model the variation found when multiple informants (either human participants or LLMs) choose REs in the same contexts. We measure the similarity of the conditional distributions of form categories using the Jensen-Shannon Divergence metric and Description Length metric. We find that the experimental methodology introduces substantial noise, but by taking this noise into account, we can model the variation captured from the corpus and RE form choices made during experiments. Furthermore, we compared the three conditional distributions over the corpus, the human experimental results, and the GPT models. Against our expectations, the divergence is greatest between the corpus and the GPT model.</abstract>
<identifier type="citekey">ellison-same-2024-experimental</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.597</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>6838</start>
<end>6848</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Experimental versus In-Corpus Variation in Referring Expression Choice
%A Ellison, T. Mark
%A Same, Fahime
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F ellison-same-2024-experimental
%X In this paper, we compare the results of three studies. The first explored feature-conditioned distributions of referring expression (RE) forms in the original corpus from which the contexts were taken. The second is a crowdsourcing study in which we asked participants to express entities within a pre-existing context, given fully specified referents. The third study replicates the crowdsourcing experiment using Large Language Models (LLMs). We evaluate how well the corpus itself can model the variation found when multiple informants (either human participants or LLMs) choose REs in the same contexts. We measure the similarity of the conditional distributions of form categories using the Jensen-Shannon Divergence metric and Description Length metric. We find that the experimental methodology introduces substantial noise, but by taking this noise into account, we can model the variation captured from the corpus and RE form choices made during experiments. Furthermore, we compared the three conditional distributions over the corpus, the human experimental results, and the GPT models. Against our expectations, the divergence is greatest between the corpus and the GPT model.
%U https://aclanthology.org/2024.lrec-main.597
%P 6838-6848
Markdown (Informal)
[Experimental versus In-Corpus Variation in Referring Expression Choice](https://aclanthology.org/2024.lrec-main.597) (Ellison & Same, LREC-COLING 2024)
ACL