@inproceedings{mykowiecka-marciniak-2019-experiments,
title = "Experiments with ad hoc ambiguous abbreviation expansion",
author = "Mykowiecka, Agnieszka and
Marciniak, Malgorzata",
editor = "Holderness, Eben and
Jimeno Yepes, Antonio and
Lavelli, Alberto and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)",
month = nov,
year = "2019",
address = "Hong Kong",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-6207",
doi = "10.18653/v1/D19-6207",
pages = "44--53",
abstract = "The paper addresses experiments to expand ad hoc ambiguous abbreviations in medical notes on the basis of morphologically annotated texts, without using additional domain resources. We work on Polish data but the described approaches can be used for other languages too. We test two methods to select candidates for word abbreviation expansions. The first one automatically selects all words in text which might be an expansion of an abbreviation according to the language rules. The second method uses clustering of abbreviation occurrences to select representative elements which are manually annotated to determine lists of potential expansions. We then train a classifier to assign expansions to abbreviations based on three training sets: automatically obtained, consisting of manual annotation, and concatenation of the two previous ones. The results obtained for the manually annotated training data significantly outperform automatically obtained training data. Adding the automatically obtained training data to the manually annotated data improves the results, in particular for less frequent abbreviations. In this context the proposed a priori data driven selection of possible extensions turned out to be crucial.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mykowiecka-marciniak-2019-experiments">
<titleInfo>
<title>Experiments with ad hoc ambiguous abbreviation expansion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Mykowiecka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malgorzata</namePart>
<namePart type="family">Marciniak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper addresses experiments to expand ad hoc ambiguous abbreviations in medical notes on the basis of morphologically annotated texts, without using additional domain resources. We work on Polish data but the described approaches can be used for other languages too. We test two methods to select candidates for word abbreviation expansions. The first one automatically selects all words in text which might be an expansion of an abbreviation according to the language rules. The second method uses clustering of abbreviation occurrences to select representative elements which are manually annotated to determine lists of potential expansions. We then train a classifier to assign expansions to abbreviations based on three training sets: automatically obtained, consisting of manual annotation, and concatenation of the two previous ones. The results obtained for the manually annotated training data significantly outperform automatically obtained training data. Adding the automatically obtained training data to the manually annotated data improves the results, in particular for less frequent abbreviations. In this context the proposed a priori data driven selection of possible extensions turned out to be crucial.</abstract>
<identifier type="citekey">mykowiecka-marciniak-2019-experiments</identifier>
<identifier type="doi">10.18653/v1/D19-6207</identifier>
<location>
<url>https://aclanthology.org/D19-6207</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>44</start>
<end>53</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Experiments with ad hoc ambiguous abbreviation expansion
%A Mykowiecka, Agnieszka
%A Marciniak, Malgorzata
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong
%F mykowiecka-marciniak-2019-experiments
%X The paper addresses experiments to expand ad hoc ambiguous abbreviations in medical notes on the basis of morphologically annotated texts, without using additional domain resources. We work on Polish data but the described approaches can be used for other languages too. We test two methods to select candidates for word abbreviation expansions. The first one automatically selects all words in text which might be an expansion of an abbreviation according to the language rules. The second method uses clustering of abbreviation occurrences to select representative elements which are manually annotated to determine lists of potential expansions. We then train a classifier to assign expansions to abbreviations based on three training sets: automatically obtained, consisting of manual annotation, and concatenation of the two previous ones. The results obtained for the manually annotated training data significantly outperform automatically obtained training data. Adding the automatically obtained training data to the manually annotated data improves the results, in particular for less frequent abbreviations. In this context the proposed a priori data driven selection of possible extensions turned out to be crucial.
%R 10.18653/v1/D19-6207
%U https://aclanthology.org/D19-6207
%U https://doi.org/10.18653/v1/D19-6207
%P 44-53
Markdown (Informal)
[Experiments with ad hoc ambiguous abbreviation expansion](https://aclanthology.org/D19-6207) (Mykowiecka & Marciniak, Louhi 2019)
ACL
- Agnieszka Mykowiecka and Malgorzata Marciniak. 2019. Experiments with ad hoc ambiguous abbreviation expansion. In Proceedings of the Tenth International Workshop on Health Text Mining and Information Analysis (LOUHI 2019), pages 44–53, Hong Kong. Association for Computational Linguistics.