@inproceedings{sheikh-etal-2016-diachronic,
title = "How Diachronic Text Corpora Affect Context based Retrieval of {OOV} Proper Names for Audio News",
author = "Sheikh, Imran and
Illina, Irina and
Fohr, Dominique",
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/L16-1609",
pages = "3851--3855",
abstract = "Out-Of-Vocabulary (OOV) words missed by Large Vocabulary Continuous Speech Recognition (LVCSR) systems can be recovered with the help of topic and semantic context of the OOV words captured from a diachronic text corpus. In this paper we investigate how the choice of documents for the diachronic text corpora affects the retrieval of OOV Proper Names (PNs) relevant to an audio document. We first present our diachronic French broadcast news datasets, which highlight the motivation of our study on OOV PNs. Then the effect of using diachronic text data from different sources and a different time span is analysed. With OOV PN retrieval experiments on French broadcast news videos, we conclude that a diachronic corpus with text from different sources leads to better retrieval performance than one relying on text from single source or from a longer time span.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sheikh-etal-2016-diachronic">
<titleInfo>
<title>How Diachronic Text Corpora Affect Context based Retrieval of OOV Proper Names for Audio News</title>
</titleInfo>
<name type="personal">
<namePart type="given">Imran</namePart>
<namePart type="family">Sheikh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Irina</namePart>
<namePart type="family">Illina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dominique</namePart>
<namePart type="family">Fohr</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>Out-Of-Vocabulary (OOV) words missed by Large Vocabulary Continuous Speech Recognition (LVCSR) systems can be recovered with the help of topic and semantic context of the OOV words captured from a diachronic text corpus. In this paper we investigate how the choice of documents for the diachronic text corpora affects the retrieval of OOV Proper Names (PNs) relevant to an audio document. We first present our diachronic French broadcast news datasets, which highlight the motivation of our study on OOV PNs. Then the effect of using diachronic text data from different sources and a different time span is analysed. With OOV PN retrieval experiments on French broadcast news videos, we conclude that a diachronic corpus with text from different sources leads to better retrieval performance than one relying on text from single source or from a longer time span.</abstract>
<identifier type="citekey">sheikh-etal-2016-diachronic</identifier>
<location>
<url>https://aclanthology.org/L16-1609</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3851</start>
<end>3855</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Diachronic Text Corpora Affect Context based Retrieval of OOV Proper Names for Audio News
%A Sheikh, Imran
%A Illina, Irina
%A Fohr, Dominique
%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 sheikh-etal-2016-diachronic
%X Out-Of-Vocabulary (OOV) words missed by Large Vocabulary Continuous Speech Recognition (LVCSR) systems can be recovered with the help of topic and semantic context of the OOV words captured from a diachronic text corpus. In this paper we investigate how the choice of documents for the diachronic text corpora affects the retrieval of OOV Proper Names (PNs) relevant to an audio document. We first present our diachronic French broadcast news datasets, which highlight the motivation of our study on OOV PNs. Then the effect of using diachronic text data from different sources and a different time span is analysed. With OOV PN retrieval experiments on French broadcast news videos, we conclude that a diachronic corpus with text from different sources leads to better retrieval performance than one relying on text from single source or from a longer time span.
%U https://aclanthology.org/L16-1609
%P 3851-3855
Markdown (Informal)
[How Diachronic Text Corpora Affect Context based Retrieval of OOV Proper Names for Audio News](https://aclanthology.org/L16-1609) (Sheikh et al., LREC 2016)
ACL