@inproceedings{zhou-etal-2021-pie,
title = "{PIE}: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing",
author = "Zhou, Jianing and
Gong, Hongyu and
Bhat, Suma",
editor = "Cook, Paul and
Mitrovi{\'c}, Jelena and
Escart{\'\i}n, Carla Parra and
Vaidya, Ashwini and
Osenova, Petya and
Taslimipoor, Shiva and
Ramisch, Carlos",
booktitle = "Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.mwe-1.5",
doi = "10.18653/v1/2021.mwe-1.5",
pages = "33--48",
abstract = "Idiomatic expressions (IE) play an important role in natural language, and have long been a {``}pain in the neck{''} for NLP systems. Despite this, text generation tasks related to IEs remain largely under-explored. In this paper, we propose two new tasks of idiomatic sentence generation and paraphrasing to fill this research gap. We introduce a curated dataset of 823 IEs, and a parallel corpus with sentences containing them and the same sentences where the IEs were replaced by their literal paraphrases as the primary resource for our tasks. We benchmark existing deep learning models, which have state-of-the-art performance on related tasks using automated and manual evaluation with our dataset to inspire further research on our proposed tasks. By establishing baseline models, we pave the way for more comprehensive and accurate modeling of IEs, both for generation and paraphrasing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2021-pie">
<titleInfo>
<title>PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jianing</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suma</namePart>
<namePart type="family">Bhat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cook</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jelena</namePart>
<namePart type="family">Mitrović</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carla</namePart>
<namePart type="given">Parra</namePart>
<namePart type="family">Escartín</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashwini</namePart>
<namePart type="family">Vaidya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiva</namePart>
<namePart type="family">Taslimipoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carlos</namePart>
<namePart type="family">Ramisch</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>Idiomatic expressions (IE) play an important role in natural language, and have long been a “pain in the neck” for NLP systems. Despite this, text generation tasks related to IEs remain largely under-explored. In this paper, we propose two new tasks of idiomatic sentence generation and paraphrasing to fill this research gap. We introduce a curated dataset of 823 IEs, and a parallel corpus with sentences containing them and the same sentences where the IEs were replaced by their literal paraphrases as the primary resource for our tasks. We benchmark existing deep learning models, which have state-of-the-art performance on related tasks using automated and manual evaluation with our dataset to inspire further research on our proposed tasks. By establishing baseline models, we pave the way for more comprehensive and accurate modeling of IEs, both for generation and paraphrasing.</abstract>
<identifier type="citekey">zhou-etal-2021-pie</identifier>
<identifier type="doi">10.18653/v1/2021.mwe-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.mwe-1.5</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>33</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing
%A Zhou, Jianing
%A Gong, Hongyu
%A Bhat, Suma
%Y Cook, Paul
%Y Mitrović, Jelena
%Y Escartín, Carla Parra
%Y Vaidya, Ashwini
%Y Osenova, Petya
%Y Taslimipoor, Shiva
%Y Ramisch, Carlos
%S Proceedings of the 17th Workshop on Multiword Expressions (MWE 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F zhou-etal-2021-pie
%X Idiomatic expressions (IE) play an important role in natural language, and have long been a “pain in the neck” for NLP systems. Despite this, text generation tasks related to IEs remain largely under-explored. In this paper, we propose two new tasks of idiomatic sentence generation and paraphrasing to fill this research gap. We introduce a curated dataset of 823 IEs, and a parallel corpus with sentences containing them and the same sentences where the IEs were replaced by their literal paraphrases as the primary resource for our tasks. We benchmark existing deep learning models, which have state-of-the-art performance on related tasks using automated and manual evaluation with our dataset to inspire further research on our proposed tasks. By establishing baseline models, we pave the way for more comprehensive and accurate modeling of IEs, both for generation and paraphrasing.
%R 10.18653/v1/2021.mwe-1.5
%U https://aclanthology.org/2021.mwe-1.5
%U https://doi.org/10.18653/v1/2021.mwe-1.5
%P 33-48
Markdown (Informal)
[PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing](https://aclanthology.org/2021.mwe-1.5) (Zhou et al., MWE 2021)
ACL