@inproceedings{bick-2016-morphological,
title = "A Morphological Lexicon of {E}speranto with Morpheme Frequencies",
author = "Bick, Eckhard",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1171/",
pages = "1075--1078",
abstract = "This paper discusses the internal structure of complex Esperanto words (CWs). Using a morphological analyzer, possible affixation and compounding is checked for over 50,000 Esperanto lexemes against a list of 17,000 root words. Morpheme boundaries in the resulting analyses were then checked manually, creating a CW dictionary of 28,000 words, representing 56.4{\%} of the lexicon, or 19.4{\%} of corpus tokens. The error percentage of the EspGram morphological analyzer for new corpus CWs was 4.3{\%} for types and 6.4{\%} for tokens, with a recall of almost 100{\%}, and wrong/spurious boundaries being more common than missing ones. For pedagogical purposes a morpheme frequency dictionary was constructed for a 16 million word corpus, confirming the importance of agglutinative derivational morphemes in the Esperanto lexicon. Finally, as a means to reduce the morphological ambiguity of CWs, we provide POS likelihoods for Esperanto suffixes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bick-2016-morphological">
<titleInfo>
<title>A Morphological Lexicon of Esperanto with Morpheme Frequencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eckhard</namePart>
<namePart type="family">Bick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses the internal structure of complex Esperanto words (CWs). Using a morphological analyzer, possible affixation and compounding is checked for over 50,000 Esperanto lexemes against a list of 17,000 root words. Morpheme boundaries in the resulting analyses were then checked manually, creating a CW dictionary of 28,000 words, representing 56.4% of the lexicon, or 19.4% of corpus tokens. The error percentage of the EspGram morphological analyzer for new corpus CWs was 4.3% for types and 6.4% for tokens, with a recall of almost 100%, and wrong/spurious boundaries being more common than missing ones. For pedagogical purposes a morpheme frequency dictionary was constructed for a 16 million word corpus, confirming the importance of agglutinative derivational morphemes in the Esperanto lexicon. Finally, as a means to reduce the morphological ambiguity of CWs, we provide POS likelihoods for Esperanto suffixes.</abstract>
<identifier type="citekey">bick-2016-morphological</identifier>
<location>
<url>https://aclanthology.org/L16-1171/</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1075</start>
<end>1078</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Morphological Lexicon of Esperanto with Morpheme Frequencies
%A Bick, Eckhard
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F bick-2016-morphological
%X This paper discusses the internal structure of complex Esperanto words (CWs). Using a morphological analyzer, possible affixation and compounding is checked for over 50,000 Esperanto lexemes against a list of 17,000 root words. Morpheme boundaries in the resulting analyses were then checked manually, creating a CW dictionary of 28,000 words, representing 56.4% of the lexicon, or 19.4% of corpus tokens. The error percentage of the EspGram morphological analyzer for new corpus CWs was 4.3% for types and 6.4% for tokens, with a recall of almost 100%, and wrong/spurious boundaries being more common than missing ones. For pedagogical purposes a morpheme frequency dictionary was constructed for a 16 million word corpus, confirming the importance of agglutinative derivational morphemes in the Esperanto lexicon. Finally, as a means to reduce the morphological ambiguity of CWs, we provide POS likelihoods for Esperanto suffixes.
%U https://aclanthology.org/L16-1171/
%P 1075-1078
Markdown (Informal)
[A Morphological Lexicon of Esperanto with Morpheme Frequencies](https://aclanthology.org/L16-1171/) (Bick, LREC 2016)
ACL