@inproceedings{grabar-eshkol-taravela-2016-detection,
title = "Detection of Reformulations in Spoken {F}rench",
author = "Grabar, Natalia and
Eshkol-Taravela, Iris",
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/L16-1596",
pages = "3760--3767",
abstract = "Our work addresses automatic detection of enunciations and segments with reformulations in French spoken corpora. The proposed approach is syntagmatic. It is based on reformulation markers and specificities of spoken language. The reference data are built manually and have gone through consensus. Automatic methods, based on rules and CRF machine learning, are proposed in order to detect the enunciations and segments that contain reformulations. With the CRF models, different features are exploited within a window of various sizes. Detection of enunciations with reformulations shows up to 0.66 precision. The tests performed for the detection of reformulated segments indicate that the task remains difficult. The best average performance values reach up to 0.65 F-measure, 0.75 precision, and 0.63 recall. We have several perspectives to this work for improving the detection of reformulated segments and for studying the data from other points of view.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grabar-eshkol-taravela-2016-detection">
<titleInfo>
<title>Detection of Reformulations in Spoken French</title>
</titleInfo>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Grabar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iris</namePart>
<namePart type="family">Eshkol-Taravela</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>Our work addresses automatic detection of enunciations and segments with reformulations in French spoken corpora. The proposed approach is syntagmatic. It is based on reformulation markers and specificities of spoken language. The reference data are built manually and have gone through consensus. Automatic methods, based on rules and CRF machine learning, are proposed in order to detect the enunciations and segments that contain reformulations. With the CRF models, different features are exploited within a window of various sizes. Detection of enunciations with reformulations shows up to 0.66 precision. The tests performed for the detection of reformulated segments indicate that the task remains difficult. The best average performance values reach up to 0.65 F-measure, 0.75 precision, and 0.63 recall. We have several perspectives to this work for improving the detection of reformulated segments and for studying the data from other points of view.</abstract>
<identifier type="citekey">grabar-eshkol-taravela-2016-detection</identifier>
<location>
<url>https://aclanthology.org/L16-1596</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3760</start>
<end>3767</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Detection of Reformulations in Spoken French
%A Grabar, Natalia
%A Eshkol-Taravela, Iris
%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 grabar-eshkol-taravela-2016-detection
%X Our work addresses automatic detection of enunciations and segments with reformulations in French spoken corpora. The proposed approach is syntagmatic. It is based on reformulation markers and specificities of spoken language. The reference data are built manually and have gone through consensus. Automatic methods, based on rules and CRF machine learning, are proposed in order to detect the enunciations and segments that contain reformulations. With the CRF models, different features are exploited within a window of various sizes. Detection of enunciations with reformulations shows up to 0.66 precision. The tests performed for the detection of reformulated segments indicate that the task remains difficult. The best average performance values reach up to 0.65 F-measure, 0.75 precision, and 0.63 recall. We have several perspectives to this work for improving the detection of reformulated segments and for studying the data from other points of view.
%U https://aclanthology.org/L16-1596
%P 3760-3767
Markdown (Informal)
[Detection of Reformulations in Spoken French](https://aclanthology.org/L16-1596) (Grabar & Eshkol-Taravela, LREC 2016)
ACL
- Natalia Grabar and Iris Eshkol-Taravela. 2016. Detection of Reformulations in Spoken French. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), pages 3760–3767, Portorož, Slovenia. European Language Resources Association (ELRA).