@inproceedings{hoenen-2016-wikipedia,
title = "{W}ikipedia Titles As Noun Tag Predictors",
author = "Hoenen, Armin",
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/L16-1335",
pages = "2114--2118",
abstract = "In this paper, we investigate a covert labeling cue, namely the probability that a title (by example of the Wikipedia titles) is a noun. If this probability is very large, any list such as or comparable to the Wikipedia titles can be used as a reliable word-class (or part-of-speech tag) predictor or noun lexicon. This may be especially useful in the case of Low Resource Languages (LRL) where labeled data is lacking and putatively for Natural Language Processing (NLP) tasks such as Word Sense Disambiguation, Sentiment Analysis and Machine Translation. Profitting from the ease of digital publication on the web as opposed to print, LRL speaker communities produce resources such as Wikipedia and Wiktionary, which can be used for an assessment. We provide statistical evidence for a strong noun bias for the Wikipedia titles from 2 corpora (English, Persian) and a dictionary (Japanese) and for a typologically balanced set of 17 languages including LRLs. Additionally, we conduct a small experiment on predicting noun tags for out-of-vocabulary items in part-of-speech tagging for English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hoenen-2016-wikipedia">
<titleInfo>
<title>Wikipedia Titles As Noun Tag Predictors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Armin</namePart>
<namePart type="family">Hoenen</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>In this paper, we investigate a covert labeling cue, namely the probability that a title (by example of the Wikipedia titles) is a noun. If this probability is very large, any list such as or comparable to the Wikipedia titles can be used as a reliable word-class (or part-of-speech tag) predictor or noun lexicon. This may be especially useful in the case of Low Resource Languages (LRL) where labeled data is lacking and putatively for Natural Language Processing (NLP) tasks such as Word Sense Disambiguation, Sentiment Analysis and Machine Translation. Profitting from the ease of digital publication on the web as opposed to print, LRL speaker communities produce resources such as Wikipedia and Wiktionary, which can be used for an assessment. We provide statistical evidence for a strong noun bias for the Wikipedia titles from 2 corpora (English, Persian) and a dictionary (Japanese) and for a typologically balanced set of 17 languages including LRLs. Additionally, we conduct a small experiment on predicting noun tags for out-of-vocabulary items in part-of-speech tagging for English.</abstract>
<identifier type="citekey">hoenen-2016-wikipedia</identifier>
<location>
<url>https://aclanthology.org/L16-1335</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>2114</start>
<end>2118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Wikipedia Titles As Noun Tag Predictors
%A Hoenen, Armin
%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 hoenen-2016-wikipedia
%X In this paper, we investigate a covert labeling cue, namely the probability that a title (by example of the Wikipedia titles) is a noun. If this probability is very large, any list such as or comparable to the Wikipedia titles can be used as a reliable word-class (or part-of-speech tag) predictor or noun lexicon. This may be especially useful in the case of Low Resource Languages (LRL) where labeled data is lacking and putatively for Natural Language Processing (NLP) tasks such as Word Sense Disambiguation, Sentiment Analysis and Machine Translation. Profitting from the ease of digital publication on the web as opposed to print, LRL speaker communities produce resources such as Wikipedia and Wiktionary, which can be used for an assessment. We provide statistical evidence for a strong noun bias for the Wikipedia titles from 2 corpora (English, Persian) and a dictionary (Japanese) and for a typologically balanced set of 17 languages including LRLs. Additionally, we conduct a small experiment on predicting noun tags for out-of-vocabulary items in part-of-speech tagging for English.
%U https://aclanthology.org/L16-1335
%P 2114-2118
Markdown (Informal)
[Wikipedia Titles As Noun Tag Predictors](https://aclanthology.org/L16-1335) (Hoenen, LREC 2016)
ACL
- Armin Hoenen. 2016. Wikipedia Titles As Noun Tag Predictors. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 2114–2118, Portorož, Slovenia. European Language Resources Association (ELRA).