Exploring temporal context in diachronic text documents for automatic OOV proper name retrieval

Imane Nkairi 1 Irina Illina 1 Georges Linarès 2 Dominique Fohr 1
1 PAROLE - Analysis, perception and recognition of speech
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : Proper name recognition is a challenging task in information retrieval in large audio/video databases. Proper names are semantically rich and are usually key to understanding the information contained in a document. Our work focuses on increasing the vocabulary coverage of a speech transcription system by automatically retrieving proper names from contemporary diachronic text documents. We proposed methods that dynamically augment the automatic speech recognition system vocabulary, using lexical and temporal features in diachronic documents. We also studied different metrics for proper name selection in order to limit the vocabulary augmentation and therefore the impact on the ASR performances. Recognition results show a significant reduction of the word error rate using augmented vocabulary.
Type de document :
Communication dans un congrès
Language & Technology Conference, Dec 2013, Poznań, Poland. pp.540-544, 2013
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00924696
Contributeur : Dominique Fohr <>
Soumis le : mardi 7 janvier 2014 - 10:05:40
Dernière modification le : mardi 18 décembre 2018 - 16:38:02

Identifiants

  • HAL Id : hal-00924696, version 1

Citation

Imane Nkairi, Irina Illina, Georges Linarès, Dominique Fohr. Exploring temporal context in diachronic text documents for automatic OOV proper name retrieval. Language & Technology Conference, Dec 2013, Poznań, Poland. pp.540-544, 2013. 〈hal-00924696〉

Partager

Métriques

Consultations de la notice

412