@inproceedings{4cf5a44ef2234a10a08df439a1d6905b,
title = "PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing",
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.",
author = "Jianing Zhou and Hongyu Gong and Suma Bhat",
note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics.; 17th Workshop on Multiword Expressions, MWE 2021 ; Conference date: 06-08-2021",
year = "2021",
language = "English (US)",
series = "MWE 2021 - 17th Workshop on Multiword Expressions, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "33--48",
editor = "Paul Cook and Jelena Mitrovic and Escartin, {Carla Parra} and Ashwini Vaidya and Petya Osenova and Shiva Taslimipoor and Carlos Ramisch",
booktitle = "MWE 2021 - 17th Workshop on Multiword Expressions, Proceedings of the Workshop",
}