@inproceedings{laali-kosseim-2017-improving,
title = "Improving Discourse Relation Projection to Build Discourse Annotated Corpora",
author = "Laali, Majid and
Kosseim, Leila",
editor = "Mitkov, Ruslan and
Angelova, Galia",
booktitle = "Proceedings of the International Conference Recent Advances in Natural Language Processing, {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd.",
url = "https://doi.org/10.26615/978-954-452-049-6_054",
doi = "10.26615/978-954-452-049-6_054",
pages = "407--416",
abstract = "The naive approach to annotation projection is not effective to project discourse annotations from one language to another because implicit relations are often changed to explicit ones and vice-versa in the translation. In this paper, we propose a novel approach based on the intersection between statistical word-alignment models to identify unsupported discourse annotations. This approach identified 65{\%} of the unsupported annotations in the English-French parallel sentences from Europarl. By filtering out these unsupported annotations, we induced the first PDTB-style discourse annotated corpus for French from Europarl. We then used this corpus to train a classifier to identify the discourse-usage of French discourse connectives and show a 15{\%} improvement of F1-score compared to the classifier trained on the non-filtered annotations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="laali-kosseim-2017-improving">
<titleInfo>
<title>Improving Discourse Relation Projection to Build Discourse Annotated Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Majid</namePart>
<namePart type="family">Laali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leila</namePart>
<namePart type="family">Kosseim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Galia</namePart>
<namePart type="family">Angelova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd.</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The naive approach to annotation projection is not effective to project discourse annotations from one language to another because implicit relations are often changed to explicit ones and vice-versa in the translation. In this paper, we propose a novel approach based on the intersection between statistical word-alignment models to identify unsupported discourse annotations. This approach identified 65% of the unsupported annotations in the English-French parallel sentences from Europarl. By filtering out these unsupported annotations, we induced the first PDTB-style discourse annotated corpus for French from Europarl. We then used this corpus to train a classifier to identify the discourse-usage of French discourse connectives and show a 15% improvement of F1-score compared to the classifier trained on the non-filtered annotations.</abstract>
<identifier type="citekey">laali-kosseim-2017-improving</identifier>
<identifier type="doi">10.26615/978-954-452-049-6_054</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>407</start>
<end>416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Discourse Relation Projection to Build Discourse Annotated Corpora
%A Laali, Majid
%A Kosseim, Leila
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F laali-kosseim-2017-improving
%X The naive approach to annotation projection is not effective to project discourse annotations from one language to another because implicit relations are often changed to explicit ones and vice-versa in the translation. In this paper, we propose a novel approach based on the intersection between statistical word-alignment models to identify unsupported discourse annotations. This approach identified 65% of the unsupported annotations in the English-French parallel sentences from Europarl. By filtering out these unsupported annotations, we induced the first PDTB-style discourse annotated corpus for French from Europarl. We then used this corpus to train a classifier to identify the discourse-usage of French discourse connectives and show a 15% improvement of F1-score compared to the classifier trained on the non-filtered annotations.
%R 10.26615/978-954-452-049-6_054
%U https://doi.org/10.26615/978-954-452-049-6_054
%P 407-416
Markdown (Informal)
[Improving Discourse Relation Projection to Build Discourse Annotated Corpora](https://doi.org/10.26615/978-954-452-049-6_054) (Laali & Kosseim, RANLP 2017)
ACL