@inproceedings{liu-nouvel-2017-bambara,
title = "A {B}ambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering",
author = "Liu, Luigi Yu-Cheng and
Nouvel, Damien",
editor = "Kondrak, Greg and
Watanabe, Taro",
booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = nov,
year = "2017",
address = "Taipei, Taiwan",
publisher = "Asian Federation of Natural Language Processing",
url = "https://aclanthology.org/I17-1070",
pages = "694--703",
abstract = "In many languages such as Bambara or Arabic, tone markers (diacritics) may be written but are actually often omitted. NLP applications are confronted to ambiguities and subsequent difficulties when processing texts. To circumvent this problem, tonalization may be used, as a word sense disambiguation task, relying on context to add diacritics that partially disambiguate words as well as senses. In this paper, we describe our implementation of a Bambara tonalizer that adds tone markers using machine learning (CRFs). To make our tool efficient, we used differential coding, word segmentation and edit operation filtering. We describe our approach that allows tractable machine learning and improves accuracy: our model may be learned within minutes on a 358K-word corpus and reaches 92.3{\%} accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-nouvel-2017-bambara">
<titleInfo>
<title>A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luigi</namePart>
<namePart type="given">Yu-Cheng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Nouvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Greg</namePart>
<namePart type="family">Kondrak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taro</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Asian Federation of Natural Language Processing</publisher>
<place>
<placeTerm type="text">Taipei, Taiwan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In many languages such as Bambara or Arabic, tone markers (diacritics) may be written but are actually often omitted. NLP applications are confronted to ambiguities and subsequent difficulties when processing texts. To circumvent this problem, tonalization may be used, as a word sense disambiguation task, relying on context to add diacritics that partially disambiguate words as well as senses. In this paper, we describe our implementation of a Bambara tonalizer that adds tone markers using machine learning (CRFs). To make our tool efficient, we used differential coding, word segmentation and edit operation filtering. We describe our approach that allows tractable machine learning and improves accuracy: our model may be learned within minutes on a 358K-word corpus and reaches 92.3% accuracy.</abstract>
<identifier type="citekey">liu-nouvel-2017-bambara</identifier>
<location>
<url>https://aclanthology.org/I17-1070</url>
</location>
<part>
<date>2017-11</date>
<extent unit="page">
<start>694</start>
<end>703</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering
%A Liu, Luigi Yu-Cheng
%A Nouvel, Damien
%Y Kondrak, Greg
%Y Watanabe, Taro
%S Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2017
%8 November
%I Asian Federation of Natural Language Processing
%C Taipei, Taiwan
%F liu-nouvel-2017-bambara
%X In many languages such as Bambara or Arabic, tone markers (diacritics) may be written but are actually often omitted. NLP applications are confronted to ambiguities and subsequent difficulties when processing texts. To circumvent this problem, tonalization may be used, as a word sense disambiguation task, relying on context to add diacritics that partially disambiguate words as well as senses. In this paper, we describe our implementation of a Bambara tonalizer that adds tone markers using machine learning (CRFs). To make our tool efficient, we used differential coding, word segmentation and edit operation filtering. We describe our approach that allows tractable machine learning and improves accuracy: our model may be learned within minutes on a 358K-word corpus and reaches 92.3% accuracy.
%U https://aclanthology.org/I17-1070
%P 694-703
Markdown (Informal)
[A Bambara Tonalization System for Word Sense Disambiguation Using Differential Coding, Segmentation and Edit Operation Filtering](https://aclanthology.org/I17-1070) (Liu & Nouvel, IJCNLP 2017)
ACL