@inproceedings{hammarstrom-etal-2008-bootstrapping,
title = "Bootstrapping Language Description: the case of {M}piemo ({B}antu {A}, {C}entral {A}frican {R}epublic)",
author = {Hammarstr{\"o}m, Harald and
Thornell, Christina and
Petzell, Malin and
Westerlund, Torbj{\"o}rn},
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/848_paper.pdf",
abstract = "Linguists have long been producing grammatical decriptions of yet undescribed languages. This is a time-consuming process, which has already adapted to improved technology for recording and storage. We present here a novel application of NLP techniques to bootstrap analysis of collected data and speed-up manual selection work. To be more precise, we argue that unsupervised induction of morphology and part-of-speech analysis from raw text data is mature enough to produce useful results. Experiments with Latent Semantic Analysis were less fruitful. We exemplify this on Mpiemo, a so-far essentially undescribed Bantu language of the Central African Republic, for which raw text data was available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hammarstrom-etal-2008-bootstrapping">
<titleInfo>
<title>Bootstrapping Language Description: the case of Mpiemo (Bantu A, Central African Republic)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harald</namePart>
<namePart type="family">Hammarström</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Thornell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Malin</namePart>
<namePart type="family">Petzell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torbjörn</namePart>
<namePart type="family">Westerlund</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Linguists have long been producing grammatical decriptions of yet undescribed languages. This is a time-consuming process, which has already adapted to improved technology for recording and storage. We present here a novel application of NLP techniques to bootstrap analysis of collected data and speed-up manual selection work. To be more precise, we argue that unsupervised induction of morphology and part-of-speech analysis from raw text data is mature enough to produce useful results. Experiments with Latent Semantic Analysis were less fruitful. We exemplify this on Mpiemo, a so-far essentially undescribed Bantu language of the Central African Republic, for which raw text data was available.</abstract>
<identifier type="citekey">hammarstrom-etal-2008-bootstrapping</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/848_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Bootstrapping Language Description: the case of Mpiemo (Bantu A, Central African Republic)
%A Hammarström, Harald
%A Thornell, Christina
%A Petzell, Malin
%A Westerlund, Torbjörn
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F hammarstrom-etal-2008-bootstrapping
%X Linguists have long been producing grammatical decriptions of yet undescribed languages. This is a time-consuming process, which has already adapted to improved technology for recording and storage. We present here a novel application of NLP techniques to bootstrap analysis of collected data and speed-up manual selection work. To be more precise, we argue that unsupervised induction of morphology and part-of-speech analysis from raw text data is mature enough to produce useful results. Experiments with Latent Semantic Analysis were less fruitful. We exemplify this on Mpiemo, a so-far essentially undescribed Bantu language of the Central African Republic, for which raw text data was available.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/848_paper.pdf
Markdown (Informal)
[Bootstrapping Language Description: the case of Mpiemo (Bantu A, Central African Republic)](http://www.lrec-conf.org/proceedings/lrec2008/pdf/848_paper.pdf) (Hammarström et al., LREC 2008)
ACL