Successfully detecting and correcting false friends using channel profiles
Identifieur interne : 000A67 ( Main/Exploration ); précédent : 000A66; suivant : 000A68Successfully detecting and correcting false friends using channel profiles
Auteurs : Ulrich Reffle [Allemagne] ; Annette Gotscharek [Allemagne] ; Christoph Ringlstetter [Allemagne] ; Klaus U. Schulz [Allemagne]Source :
- International journal on document analysis and recognition : (Print) [ 1433-2833 ] ; 2009.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Dictionnaire.
English descriptors
- KwdEn :
Abstract
The detection and correction of false friends- also called real-word errors-is a notoriously difficult problem. On realistic data, the break-even point for automatic correction so far could not be reached: the number of additional infelicitous corrections outnumbered the useful corrections. We present a new approach where we first compute a profile of the error channel for the given text. During the correction process, the profile (1) helps to restrict attention to a small set of "suspicious" lexical tokens of the input text where it is "plausible" to assume that the token represents a false friend. In this way, recognition of false friends is improved. Furthermore, the profile (2) helps to isolate the "most promising" correction suggestion for "suspicious" tokens. Using a conventional word trigram statistics for disambiguation we obtain a correction method that can be successfully applied to unrestricted text. In experiments for OCR documents, we show significant accuracy gains by fully automatic correction of false friends.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000195
- to stream PascalFrancis, to step Curation: 000582
- to stream PascalFrancis, to step Checkpoint: 000182
- to stream Main, to step Merge: 000A76
- to stream Main, to step Curation: 000A67
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">Successfully detecting and correcting false friends using channel profiles</title>
<author><name sortKey="Reffle, Ulrich" sort="Reffle, Ulrich" uniqKey="Reffle U" first="Ulrich" last="Reffle">Ulrich Reffle</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
<author><name sortKey="Gotscharek, Annette" sort="Gotscharek, Annette" uniqKey="Gotscharek A" first="Annette" last="Gotscharek">Annette Gotscharek</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
<author><name sortKey="Ringlstetter, Christoph" sort="Ringlstetter, Christoph" uniqKey="Ringlstetter C" first="Christoph" last="Ringlstetter">Christoph Ringlstetter</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
<author><name sortKey="Schulz, Klaus U" sort="Schulz, Klaus U" uniqKey="Schulz K" first="Klaus U." last="Schulz">Klaus U. Schulz</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">10-0180628</idno>
<date when="2009">2009</date>
<idno type="stanalyst">PASCAL 10-0180628 INIST</idno>
<idno type="RBID">Pascal:10-0180628</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000195</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000582</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000182</idno>
<idno type="wicri:doubleKey">1433-2833:2009:Reffle U:successfully:detecting:and</idno>
<idno type="wicri:Area/Main/Merge">000A76</idno>
<idno type="wicri:Area/Main/Curation">000A67</idno>
<idno type="wicri:Area/Main/Exploration">000A67</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">Successfully detecting and correcting false friends using channel profiles</title>
<author><name sortKey="Reffle, Ulrich" sort="Reffle, Ulrich" uniqKey="Reffle U" first="Ulrich" last="Reffle">Ulrich Reffle</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
<author><name sortKey="Gotscharek, Annette" sort="Gotscharek, Annette" uniqKey="Gotscharek A" first="Annette" last="Gotscharek">Annette Gotscharek</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
<author><name sortKey="Ringlstetter, Christoph" sort="Ringlstetter, Christoph" uniqKey="Ringlstetter C" first="Christoph" last="Ringlstetter">Christoph Ringlstetter</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
<author><name sortKey="Schulz, Klaus U" sort="Schulz, Klaus U" uniqKey="Schulz K" first="Klaus U." last="Schulz">Klaus U. Schulz</name>
<affiliation wicri:level="4"><inist:fA14 i1="01"><s1>CIS, University of Munich, Oettingenstr 67</s1>
<s2>80538 Munich</s2>
<s3>DEU</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
<sZ>4 aut.</sZ>
</inist:fA14>
<country>Allemagne</country>
<placeName><region type="land" nuts="1">Bavière</region>
<region type="district" nuts="2">District de Haute-Bavière</region>
<settlement type="city">Munich</settlement>
</placeName>
<orgName type="university">Université Louis-et-Maximilien de Munich</orgName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
<imprint><date when="2009">2009</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">International journal on document analysis and recognition : (Print)</title>
<title level="j" type="abbreviated">Int. j. doc. anal. recognit. : (Print)</title>
<idno type="ISSN">1433-2833</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Automatic correction</term>
<term>Character recognition</term>
<term>Dictionaries</term>
<term>Disambiguation</term>
<term>Error correction</term>
<term>Optical character recognition</term>
<term>Probabilistic approach</term>
<term>Statistical analysis</term>
<term>Text</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Texte</term>
<term>Reconnaissance caractère</term>
<term>Reconnaissance optique caractère</term>
<term>Dictionnaire</term>
<term>Correction automatique</term>
<term>Désambiguïsation</term>
<term>Analyse statistique</term>
<term>Approche probabiliste</term>
<term>Correction erreur</term>
<term>.</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Dictionnaire</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">The detection and correction of false friends- also called real-word errors-is a notoriously difficult problem. On realistic data, the break-even point for automatic correction so far could not be reached: the number of additional infelicitous corrections outnumbered the useful corrections. We present a new approach where we first compute a profile of the error channel for the given text. During the correction process, the profile (1) helps to restrict attention to a small set of "suspicious" lexical tokens of the input text where it is "plausible" to assume that the token represents a false friend. In this way, recognition of false friends is improved. Furthermore, the profile (2) helps to isolate the "most promising" correction suggestion for "suspicious" tokens. Using a conventional word trigram statistics for disambiguation we obtain a correction method that can be successfully applied to unrestricted text. In experiments for OCR documents, we show significant accuracy gains by fully automatic correction of false friends.</div>
</front>
</TEI>
<affiliations><list><country><li>Allemagne</li>
</country>
<region><li>Bavière</li>
<li>District de Haute-Bavière</li>
</region>
<settlement><li>Munich</li>
</settlement>
<orgName><li>Université Louis-et-Maximilien de Munich</li>
</orgName>
</list>
<tree><country name="Allemagne"><region name="Bavière"><name sortKey="Reffle, Ulrich" sort="Reffle, Ulrich" uniqKey="Reffle U" first="Ulrich" last="Reffle">Ulrich Reffle</name>
</region>
<name sortKey="Gotscharek, Annette" sort="Gotscharek, Annette" uniqKey="Gotscharek A" first="Annette" last="Gotscharek">Annette Gotscharek</name>
<name sortKey="Ringlstetter, Christoph" sort="Ringlstetter, Christoph" uniqKey="Ringlstetter C" first="Christoph" last="Ringlstetter">Christoph Ringlstetter</name>
<name sortKey="Schulz, Klaus U" sort="Schulz, Klaus U" uniqKey="Schulz K" first="Klaus U." last="Schulz">Klaus U. Schulz</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000A67 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000A67 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Exploration |type= RBID |clé= Pascal:10-0180628 |texte= Successfully detecting and correcting false friends using channel profiles }}
This area was generated with Dilib version V0.6.32. |