@inproceedings{clark-smith-2021-choose,
title = "Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation Models",
author = "Clark, Elizabeth and
Smith, Noah A.",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.279",
doi = "10.18653/v1/2021.naacl-main.279",
pages = "3566--3575",
abstract = "Story generation is an open-ended and subjective task, which poses a challenge for evaluating story generation models. We present Choose Your Own Adventure, a collaborative writing setup for pairwise model evaluation. Two models generate suggestions to people as they write a short story; we ask writers to choose one of the two suggestions, and we observe which model{'}s suggestions they prefer. The setup also allows further analysis based on the revisions people make to the suggestions. We show that these measures, combined with automatic metrics, provide an informative picture of the models{'} performance, both in cases where the differences in generation methods are small (nucleus vs. top-k sampling) and large (GPT2 vs. Fusion models).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="clark-smith-2021-choose">
<titleInfo>
<title>Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Noah</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Story generation is an open-ended and subjective task, which poses a challenge for evaluating story generation models. We present Choose Your Own Adventure, a collaborative writing setup for pairwise model evaluation. Two models generate suggestions to people as they write a short story; we ask writers to choose one of the two suggestions, and we observe which model’s suggestions they prefer. The setup also allows further analysis based on the revisions people make to the suggestions. We show that these measures, combined with automatic metrics, provide an informative picture of the models’ performance, both in cases where the differences in generation methods are small (nucleus vs. top-k sampling) and large (GPT2 vs. Fusion models).</abstract>
<identifier type="citekey">clark-smith-2021-choose</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.279</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.279</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3566</start>
<end>3575</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation Models
%A Clark, Elizabeth
%A Smith, Noah A.
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F clark-smith-2021-choose
%X Story generation is an open-ended and subjective task, which poses a challenge for evaluating story generation models. We present Choose Your Own Adventure, a collaborative writing setup for pairwise model evaluation. Two models generate suggestions to people as they write a short story; we ask writers to choose one of the two suggestions, and we observe which model’s suggestions they prefer. The setup also allows further analysis based on the revisions people make to the suggestions. We show that these measures, combined with automatic metrics, provide an informative picture of the models’ performance, both in cases where the differences in generation methods are small (nucleus vs. top-k sampling) and large (GPT2 vs. Fusion models).
%R 10.18653/v1/2021.naacl-main.279
%U https://aclanthology.org/2021.naacl-main.279
%U https://doi.org/10.18653/v1/2021.naacl-main.279
%P 3566-3575
Markdown (Informal)
[Choose Your Own Adventure: Paired Suggestions in Collaborative Writing for Evaluating Story Generation Models](https://aclanthology.org/2021.naacl-main.279) (Clark & Smith, NAACL 2021)
ACL