论文信息 - Diacritics Restoration: Learning from Letters versus Learning from Words

Diacritics Restoration: Learning from Letters versus Learning from Words

This paper presents a method for diacritics restoration based on learning mechanisms that act at letter level. This technique is new to our knowledge, and we compare it with the well known techniques for diacritics restoration that learn from words. Our method is particularly useful for languages that lack large electronic dictionaries and where means for generalization beyond words are required. Accuracies of over 99% at letter level are reported.

Rada Mihalcea | Rada Mihalcea

[1] A M Derouault. Accentuation automatique de textes par des méthodes probabilistes , 1994 .

[2] Walter Daelemans,et al. Forgetting Exceptions is Harmful in Language Learning , 1998, Machine Learning.

[3] Walter Daelemans,et al. TiMBL: Tilburg Memory-Based Learner, version 2.0, Reference guide , 1998 .

[4] David Yarowsky,et al. A Comparison of Corpus-Based Techniques for Restoring Accents in Spanish and French Text , 1999 .

[5] Peter Willett,et al. Automatic Spelling Correction Using a Trigram Similarity Measure , 1983, Inf. Process. Manag..

[6] Michel Simard. Automatic Insertion of Accents in French Text , 1998, EMNLP.

[7] J. Ross Quinlan,et al. C4.5: Programs for Machine Learning , 1992 .

[8] D. Tufi. Automatic Diacritics Insertion in Romanian Texts , 1999 .

[9] Alexander F. Gelbukh,et al. A Simple Spanish Part of Speech Tagger for Detection and Correction of Accentuation Error , 1999, TSD.