@inproceedings{pouran-ben-veyseh-etal-2020-acronym,
title = "What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation",
author = "Pouran Ben Veyseh, Amir and
Dernoncourt, Franck and
Tran, Quan Hung and
Nguyen, Thien Huu",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.292",
doi = "10.18653/v1/2020.coling-main.292",
pages = "3285--3301",
abstract = "Acronyms are the short forms of phrases that facilitate conveying lengthy sentences in documents and serve as one of the mainstays of writing. Due to their importance, identifying acronyms and corresponding phrases (i.e., acronym identification (AI)) and finding the correct meaning of each acronym (i.e., acronym disambiguation (AD)) are crucial for text understanding. Despite the recent progress on this task, there are some limitations in the existing datasets which hinder further improvement. More specifically, limited size of manually annotated AI datasets or noises in the automatically created acronym identification datasets obstruct designing advanced high-performing acronym identification models. Moreover, the existing datasets are mostly limited to the medical domain and ignore other domains. In order to address these two limitations, we first create a manually annotated large AI dataset for scientific domain. This dataset contains 17,506 sentences which is substantially larger than previous scientific AI datasets. Next, we prepare an AD dataset for scientific domain with 62,441 samples which is significantly larger than previous scientific AD dataset. Our experiments show that the existing state-of-the-art models fall far behind human-level performance on both datasets proposed by this work. In addition, we propose a new deep learning model which utilizes the syntactical structure of the sentence to expand an ambiguous acronym in a sentence. The proposed model outperforms the state-of-the-art models on the new AD dataset, providing a strong baseline for future research on this dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pouran-ben-veyseh-etal-2020-acronym">
<titleInfo>
<title>What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="family">Pouran Ben Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="given">Hung</namePart>
<namePart type="family">Tran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Acronyms are the short forms of phrases that facilitate conveying lengthy sentences in documents and serve as one of the mainstays of writing. Due to their importance, identifying acronyms and corresponding phrases (i.e., acronym identification (AI)) and finding the correct meaning of each acronym (i.e., acronym disambiguation (AD)) are crucial for text understanding. Despite the recent progress on this task, there are some limitations in the existing datasets which hinder further improvement. More specifically, limited size of manually annotated AI datasets or noises in the automatically created acronym identification datasets obstruct designing advanced high-performing acronym identification models. Moreover, the existing datasets are mostly limited to the medical domain and ignore other domains. In order to address these two limitations, we first create a manually annotated large AI dataset for scientific domain. This dataset contains 17,506 sentences which is substantially larger than previous scientific AI datasets. Next, we prepare an AD dataset for scientific domain with 62,441 samples which is significantly larger than previous scientific AD dataset. Our experiments show that the existing state-of-the-art models fall far behind human-level performance on both datasets proposed by this work. In addition, we propose a new deep learning model which utilizes the syntactical structure of the sentence to expand an ambiguous acronym in a sentence. The proposed model outperforms the state-of-the-art models on the new AD dataset, providing a strong baseline for future research on this dataset.</abstract>
<identifier type="citekey">pouran-ben-veyseh-etal-2020-acronym</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.292</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.292</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>3285</start>
<end>3301</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation
%A Pouran Ben Veyseh, Amir
%A Dernoncourt, Franck
%A Tran, Quan Hung
%A Nguyen, Thien Huu
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F pouran-ben-veyseh-etal-2020-acronym
%X Acronyms are the short forms of phrases that facilitate conveying lengthy sentences in documents and serve as one of the mainstays of writing. Due to their importance, identifying acronyms and corresponding phrases (i.e., acronym identification (AI)) and finding the correct meaning of each acronym (i.e., acronym disambiguation (AD)) are crucial for text understanding. Despite the recent progress on this task, there are some limitations in the existing datasets which hinder further improvement. More specifically, limited size of manually annotated AI datasets or noises in the automatically created acronym identification datasets obstruct designing advanced high-performing acronym identification models. Moreover, the existing datasets are mostly limited to the medical domain and ignore other domains. In order to address these two limitations, we first create a manually annotated large AI dataset for scientific domain. This dataset contains 17,506 sentences which is substantially larger than previous scientific AI datasets. Next, we prepare an AD dataset for scientific domain with 62,441 samples which is significantly larger than previous scientific AD dataset. Our experiments show that the existing state-of-the-art models fall far behind human-level performance on both datasets proposed by this work. In addition, we propose a new deep learning model which utilizes the syntactical structure of the sentence to expand an ambiguous acronym in a sentence. The proposed model outperforms the state-of-the-art models on the new AD dataset, providing a strong baseline for future research on this dataset.
%R 10.18653/v1/2020.coling-main.292
%U https://aclanthology.org/2020.coling-main.292
%U https://doi.org/10.18653/v1/2020.coling-main.292
%P 3285-3301
Markdown (Informal)
[What Does This Acronym Mean? Introducing a New Dataset for Acronym Identification and Disambiguation](https://aclanthology.org/2020.coling-main.292) (Pouran Ben Veyseh et al., COLING 2020)
ACL