@inproceedings{kwon-etal-2020-modeling,
title = "Modeling Preconditions in Text with a Crowd-sourced Dataset",
author = "Kwon, Heeyoung and
Koupaee, Mahnaz and
Singh, Pratyush and
Sawhney, Gargi and
Shukla, Anmol and
Kallur, Keerthi Kumar and
Chambers, Nathanael and
Balasubramanian, Niranjan",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.340/",
doi = "10.18653/v1/2020.findings-emnlp.340",
pages = "3818--3828",
abstract = "Preconditions provide a form of logical connection between events that explains why some events occur together and information that is complementary to the more widely studied relations such as causation, temporal ordering, entailment, and discourse relations. Modeling preconditions in text has been hampered in part due to the lack of large scale labeled data grounded in text. This paper introduces PeKo, a crowd-sourced annotation of \textit{preconditions} between event pairs in newswire, an order of magnitude larger than prior text annotations. To complement this new corpus, we also introduce two challenge tasks aimed at modeling preconditions: (i) Precondition Identification {--} a standard classification task defined over pairs of event mentions, and (ii) Precondition Generation {--} a generative task aimed at testing a more general ability to reason about a given event. Evaluation on both tasks shows that modeling preconditions is challenging even for today`s large language models (LM). This suggests that precondition knowledge is not easily accessible in LM-derived representations alone. Our generation results show that fine-tuning an LM on PeKo yields better conditional relations than when trained on raw text or temporally-ordered corpora."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kwon-etal-2020-modeling">
<titleInfo>
<title>Modeling Preconditions in Text with a Crowd-sourced Dataset</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heeyoung</namePart>
<namePart type="family">Kwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mahnaz</namePart>
<namePart type="family">Koupaee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratyush</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gargi</namePart>
<namePart type="family">Sawhney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anmol</namePart>
<namePart type="family">Shukla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keerthi</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Kallur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathanael</namePart>
<namePart type="family">Chambers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niranjan</namePart>
<namePart type="family">Balasubramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>Preconditions provide a form of logical connection between events that explains why some events occur together and information that is complementary to the more widely studied relations such as causation, temporal ordering, entailment, and discourse relations. Modeling preconditions in text has been hampered in part due to the lack of large scale labeled data grounded in text. This paper introduces PeKo, a crowd-sourced annotation of preconditions between event pairs in newswire, an order of magnitude larger than prior text annotations. To complement this new corpus, we also introduce two challenge tasks aimed at modeling preconditions: (i) Precondition Identification – a standard classification task defined over pairs of event mentions, and (ii) Precondition Generation – a generative task aimed at testing a more general ability to reason about a given event. Evaluation on both tasks shows that modeling preconditions is challenging even for today‘s large language models (LM). This suggests that precondition knowledge is not easily accessible in LM-derived representations alone. Our generation results show that fine-tuning an LM on PeKo yields better conditional relations than when trained on raw text or temporally-ordered corpora.</abstract>
<identifier type="citekey">kwon-etal-2020-modeling</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.340</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.340/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>3818</start>
<end>3828</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Modeling Preconditions in Text with a Crowd-sourced Dataset
%A Kwon, Heeyoung
%A Koupaee, Mahnaz
%A Singh, Pratyush
%A Sawhney, Gargi
%A Shukla, Anmol
%A Kallur, Keerthi Kumar
%A Chambers, Nathanael
%A Balasubramanian, Niranjan
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F kwon-etal-2020-modeling
%X Preconditions provide a form of logical connection between events that explains why some events occur together and information that is complementary to the more widely studied relations such as causation, temporal ordering, entailment, and discourse relations. Modeling preconditions in text has been hampered in part due to the lack of large scale labeled data grounded in text. This paper introduces PeKo, a crowd-sourced annotation of preconditions between event pairs in newswire, an order of magnitude larger than prior text annotations. To complement this new corpus, we also introduce two challenge tasks aimed at modeling preconditions: (i) Precondition Identification – a standard classification task defined over pairs of event mentions, and (ii) Precondition Generation – a generative task aimed at testing a more general ability to reason about a given event. Evaluation on both tasks shows that modeling preconditions is challenging even for today‘s large language models (LM). This suggests that precondition knowledge is not easily accessible in LM-derived representations alone. Our generation results show that fine-tuning an LM on PeKo yields better conditional relations than when trained on raw text or temporally-ordered corpora.
%R 10.18653/v1/2020.findings-emnlp.340
%U https://aclanthology.org/2020.findings-emnlp.340/
%U https://doi.org/10.18653/v1/2020.findings-emnlp.340
%P 3818-3828
Markdown (Informal)
[Modeling Preconditions in Text with a Crowd-sourced Dataset](https://aclanthology.org/2020.findings-emnlp.340/) (Kwon et al., Findings 2020)
ACL
- Heeyoung Kwon, Mahnaz Koupaee, Pratyush Singh, Gargi Sawhney, Anmol Shukla, Keerthi Kumar Kallur, Nathanael Chambers, and Niranjan Balasubramanian. 2020. Modeling Preconditions in Text with a Crowd-sourced Dataset. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3818–3828, Online. Association for Computational Linguistics.