@inproceedings{sakaguchi-etal-2021-proscript-partially,
title = "pro{S}cript: Partially Ordered Scripts Generation",
author = "Sakaguchi, Keisuke and
Bhagavatula, Chandra and
Le Bras, Ronan and
Tandon, Niket and
Clark, Peter and
Choi, Yejin",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.184",
doi = "10.18653/v1/2021.findings-emnlp.184",
pages = "2138--2149",
abstract = "Scripts {--} prototypical event sequences describing everyday activities {--} have been shown to help understand narratives by providing expectations, resolving ambiguity, and filling in unstated information. However, to date they have proved hard to author or extract from text. In this work, we demonstrate for the first time that pre-trained neural language models can be finetuned to generate high-quality scripts, at varying levels of granularity, for a wide range of everyday scenarios (e.g., bake a cake). To do this, we collect a large (6.4k) crowdsourced partially ordered scripts (named proScript), that is substantially larger than prior datasets, and develop models that generate scripts by combining language generation and graph structure prediction. We define two complementary tasks: (i) edge prediction: given a scenario and unordered events, organize the events into a valid (possibly partial-order) script, and (ii) script generation: given only a scenario, generate events and organize them into a (possibly partial-order) script. Our experiments show that our models perform well (e.g., F1=75.7 on task (i)), illustrating a new approach to overcoming previous barriers to script collection. We also show that there is still significant room for improvement toward human level performance. Together, our tasks, dataset, and models offer a new research direction for learning script knowledge.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakaguchi-etal-2021-proscript-partially">
<titleInfo>
<title>proScript: Partially Ordered Scripts Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keisuke</namePart>
<namePart type="family">Sakaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chandra</namePart>
<namePart type="family">Bhagavatula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronan</namePart>
<namePart type="family">Le Bras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niket</namePart>
<namePart type="family">Tandon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Scripts – prototypical event sequences describing everyday activities – have been shown to help understand narratives by providing expectations, resolving ambiguity, and filling in unstated information. However, to date they have proved hard to author or extract from text. In this work, we demonstrate for the first time that pre-trained neural language models can be finetuned to generate high-quality scripts, at varying levels of granularity, for a wide range of everyday scenarios (e.g., bake a cake). To do this, we collect a large (6.4k) crowdsourced partially ordered scripts (named proScript), that is substantially larger than prior datasets, and develop models that generate scripts by combining language generation and graph structure prediction. We define two complementary tasks: (i) edge prediction: given a scenario and unordered events, organize the events into a valid (possibly partial-order) script, and (ii) script generation: given only a scenario, generate events and organize them into a (possibly partial-order) script. Our experiments show that our models perform well (e.g., F1=75.7 on task (i)), illustrating a new approach to overcoming previous barriers to script collection. We also show that there is still significant room for improvement toward human level performance. Together, our tasks, dataset, and models offer a new research direction for learning script knowledge.</abstract>
<identifier type="citekey">sakaguchi-etal-2021-proscript-partially</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.184</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.184</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2138</start>
<end>2149</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T proScript: Partially Ordered Scripts Generation
%A Sakaguchi, Keisuke
%A Bhagavatula, Chandra
%A Le Bras, Ronan
%A Tandon, Niket
%A Clark, Peter
%A Choi, Yejin
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F sakaguchi-etal-2021-proscript-partially
%X Scripts – prototypical event sequences describing everyday activities – have been shown to help understand narratives by providing expectations, resolving ambiguity, and filling in unstated information. However, to date they have proved hard to author or extract from text. In this work, we demonstrate for the first time that pre-trained neural language models can be finetuned to generate high-quality scripts, at varying levels of granularity, for a wide range of everyday scenarios (e.g., bake a cake). To do this, we collect a large (6.4k) crowdsourced partially ordered scripts (named proScript), that is substantially larger than prior datasets, and develop models that generate scripts by combining language generation and graph structure prediction. We define two complementary tasks: (i) edge prediction: given a scenario and unordered events, organize the events into a valid (possibly partial-order) script, and (ii) script generation: given only a scenario, generate events and organize them into a (possibly partial-order) script. Our experiments show that our models perform well (e.g., F1=75.7 on task (i)), illustrating a new approach to overcoming previous barriers to script collection. We also show that there is still significant room for improvement toward human level performance. Together, our tasks, dataset, and models offer a new research direction for learning script knowledge.
%R 10.18653/v1/2021.findings-emnlp.184
%U https://aclanthology.org/2021.findings-emnlp.184
%U https://doi.org/10.18653/v1/2021.findings-emnlp.184
%P 2138-2149
Markdown (Informal)
[proScript: Partially Ordered Scripts Generation](https://aclanthology.org/2021.findings-emnlp.184) (Sakaguchi et al., Findings 2021)
ACL
- Keisuke Sakaguchi, Chandra Bhagavatula, Ronan Le Bras, Niket Tandon, Peter Clark, and Yejin Choi. 2021. proScript: Partially Ordered Scripts Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2138–2149, Punta Cana, Dominican Republic. Association for Computational Linguistics.