Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation

Manuel Rafael Ciosici; Ira Assent

Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation

Manuel Rafael Ciosici, Ira Assent

Department of Computer Science

Research output: Contribution to book/anthology/report/proceeding › Article in proceedings › Research › peer-review

2 Citations (Scopus)

194 Downloads (Pure)

Abstract

We present Abbreviation Explorer, a system that supports interactive exploration of abbreviations that are challenging for Unsupervised Abbreviation Disambiguation (UAD). Abbreviation Explorer helps to identify long-forms that are easily confused, and to pinpoint likely causes such as limitations of normalization, language switching, or inconsistent typing. It can also support determining which long-forms would benefit from additional input text for unsupervised abbreviation disambiguation. The system provides options for creating corrective rules that merge redundant long-forms with identical meaning. The identified rules can be easily applied to the already existing vector spaces used by UAD to improve disambiguation performance, while also avoiding the cost of retraining.

Original language	English
Title of host publication	NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies - Proceedings of the Demonstrations Session
Editors	Waleed Ammar, Annie Louis, Nasrin Mostafazadeh
Number of pages	5
Place of publication	Minneapolis
Publisher	Association for Computational Linguistics
Publication date	2019
Pages	1-5
ISBN (Electronic)	9781950737161
Publication status	Published - 2019
Event	Annual Conference of the North American Chapter of the Association for Computational Linguistics - Hyatt Regency, Minneapolis, United States Duration: 3 Jun 2019 → 5 Jun 2019 https://naacl2019.org

Conference

Conference	Annual Conference of the North American Chapter of the Association for Computational Linguistics
Location	Hyatt Regency
Country/Territory	United States
City	Minneapolis
Period	03/06/2019 → 05/06/2019
Internet address	https://naacl2019.org

Access to Document

Published PaperFinal published version, 328 KB

https://aclweb.org/anthology/papers/N/N19/N19-4001/

2 Citations
1 Ph.D. thesis

Characterizing Word Representations For Natural Language Processing
Ciosici, M. R., Oct 2019, Aarhus University.
Research output: Book/anthology/dissertation/report › Ph.D. thesis

Open Access
File

Cite this

Ciosici, M. R., & Assent, I. (2019). Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation. In W. Ammar, A. Louis, & N. Mostafazadeh (Eds.), NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Demonstrations Session (pp. 1-5). Association for Computational Linguistics. https://aclweb.org/anthology/papers/N/N19/N19-4001/

Ciosici, Manuel Rafael ; Assent, Ira. / Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Demonstrations Session. editor / Waleed Ammar ; Annie Louis ; Nasrin Mostafazadeh. Minneapolis : Association for Computational Linguistics, 2019. pp. 1-5

@inproceedings{dd5d0650a6094f57906a477a39fa1997,

title = "Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation",

abstract = "We present Abbreviation Explorer, a system that supports interactive exploration of abbreviations that are challenging for Unsupervised Abbreviation Disambiguation (UAD). Abbreviation Explorer helps to identify long-forms that are easily confused, and to pinpoint likely causes such as limitations of normalization, language switching, or inconsistent typing. It can also support determining which long-forms would benefit from additional input text for unsupervised abbreviation disambiguation. The system provides options for creating corrective rules that merge redundant long-forms with identical meaning. The identified rules can be easily applied to the already existing vector spaces used by UAD to improve disambiguation performance, while also avoiding the cost of retraining.",

author = "Ciosici, {Manuel Rafael} and Ira Assent",

year = "2019",

language = "English",

pages = "1--5",

editor = "Waleed Ammar and Annie Louis and Nasrin Mostafazadeh",

booktitle = "NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics",

note = "Annual Conference of the North American Chapter of the Association for Computational Linguistics, NAACL ; Conference date: 03-06-2019 Through 05-06-2019",

url = "https://naacl2019.org",

}

Ciosici, MR & Assent, I 2019, Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation. in W Ammar, A Louis & N Mostafazadeh (eds), NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Demonstrations Session. Association for Computational Linguistics, Minneapolis, pp. 1-5, Annual Conference of the North American Chapter of the Association for Computational Linguistics, Minneapolis, United States, 03/06/2019. <https://aclweb.org/anthology/papers/N/N19/N19-4001/>

Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation. / Ciosici, Manuel Rafael ; Assent, Ira.
NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Demonstrations Session. ed. / Waleed Ammar; Annie Louis; Nasrin Mostafazadeh. Minneapolis: Association for Computational Linguistics, 2019. p. 1-5.

Research output: Contribution to book/anthology/report/proceeding › Article in proceedings › Research › peer-review

TY - GEN

T1 - Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation

AU - Ciosici, Manuel Rafael

AU - Assent, Ira

PY - 2019

Y1 - 2019

N2 - We present Abbreviation Explorer, a system that supports interactive exploration of abbreviations that are challenging for Unsupervised Abbreviation Disambiguation (UAD). Abbreviation Explorer helps to identify long-forms that are easily confused, and to pinpoint likely causes such as limitations of normalization, language switching, or inconsistent typing. It can also support determining which long-forms would benefit from additional input text for unsupervised abbreviation disambiguation. The system provides options for creating corrective rules that merge redundant long-forms with identical meaning. The identified rules can be easily applied to the already existing vector spaces used by UAD to improve disambiguation performance, while also avoiding the cost of retraining.

AB - We present Abbreviation Explorer, a system that supports interactive exploration of abbreviations that are challenging for Unsupervised Abbreviation Disambiguation (UAD). Abbreviation Explorer helps to identify long-forms that are easily confused, and to pinpoint likely causes such as limitations of normalization, language switching, or inconsistent typing. It can also support determining which long-forms would benefit from additional input text for unsupervised abbreviation disambiguation. The system provides options for creating corrective rules that merge redundant long-forms with identical meaning. The identified rules can be easily applied to the already existing vector spaces used by UAD to improve disambiguation performance, while also avoiding the cost of retraining.

M3 - Article in proceedings

SP - 1

EP - 5

BT - NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics

A2 - Ammar, Waleed

A2 - Louis, Annie

A2 - Mostafazadeh, Nasrin

PB - Association for Computational Linguistics

CY - Minneapolis

T2 - Annual Conference of the North American Chapter of the Association for Computational Linguistics

Y2 - 3 June 2019 through 5 June 2019

ER -

Ciosici MR , Assent I. Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation. In Ammar W, Louis A, Mostafazadeh N, editors, NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Demonstrations Session. Minneapolis: Association for Computational Linguistics. 2019. p. 1-5

Abbreviation Explorer - an interactive system for pre-evaluation of Unsupervised Abbreviation Disambiguation

Abstract

Conference

Access to Document

Fingerprint

Research output

Characterizing Word Representations For Natural Language Processing

Cite this