Intégration de la reconnaissance des entités nommées au processus de reconnaissance de la parole

Nous nous interessons a la tâche de reconnaissance des entites nommees pour la modalite orale. Cette tâche pose un certain nombre de difficultes qui sont inherentes aux caracteristiques intrinseques du traitement de l'oral (absence de capitalisation, manque de ponctuation, presence de disfluences et d'erreurs de reconnaissance...). Dans ce travail, nous proposons d'etudier le couplage etroit entre la tâche de transcription de la parole et la tâche de reconnaissance des entites nommees. Dans ce but, nous detournons les fonctionnalites de base d'un systeme de transcription de la parole pour le transformer en un systeme de reconnaissance des entites nommees. Ainsi, en mobilisant les connaissances propres au traitement de la parole dans le cadre de la tâche liee a la reconnaissance des entites nommees, nous assurons une plus grande synergie entre ces deux tâches. Ceci se traduit par une augmentation significative de la qualite de la reconnaissance des entites nommees d'environ 5 % en termes de SER (Slot Error Rate) comme de F-mesure, par rapport aux resultats obtenus avec l'un des meilleurs systemes de reconnaissance des entites nommees en parole lorsque celui-ci est utilise en aval de la tâche de transcription de la parole.

[1]  Ralph Weischedel,et al.  NAMED ENTITY EXTRACTION FROM SPEECH , 1998 .

[2]  Frédéric Béchet,et al.  Conceptual decoding from word lattices: application to the spoken dialogue corpus MEDIA , 2006, INTERSPEECH.

[3]  Ralph Weischedel,et al.  PERFORMANCE MEASURES FOR INFORMATION EXTRACTION , 2007 .

[4]  Guillaume Gravier,et al.  The ester 2 evaluation campaign for the rich transcription of French radio broadcasts , 2009, INTERSPEECH.

[5]  Mei-Yuh Hwang,et al.  An Overview of the SPHINX-II Speech Recognition System , 1993, HLT.

[6]  Paul Deléglise,et al.  Improvements to the LIUM French ASR system based on CMU sphinx: what helps to significantly reduce the word error rate? , 2009, INTERSPEECH.

[7]  Olivier Galibert,et al.  The ETAPE corpus for the evaluation of speech-based TV content processing in the French language , 2012, LREC.

[8]  Rohit Prasad,et al.  Robust named entity detection from optical character recognition output , 2011, International Journal on Document Analysis and Recognition (IJDAR).

[9]  Katsuhito Sudoh,et al.  Incorporating Speech Recognition Confidence into Discriminative Named Entity Recognition of Speech Data , 2006, ACL.

[10]  Atsushi Nakamura,et al.  An Extremely Large Vocabulary Approach to Named Entity Extraction from Speech , 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

[11]  Ralph Grishman,et al.  Message Understanding Conference- 6: A Brief History , 1996, COLING.

[12]  Mark A. Przybocki,et al.  The Automatic Content Extraction (ACE) Program – Tasks, Data, and Evaluation , 2004, LREC.

[13]  Mark Dredze,et al.  OOV Sensitive Named-Entity Recognition in Speech , 2011, INTERSPEECH.

[14]  Bhuvana Ramabhadran,et al.  Leveraging word confusion networks for named entity modeling and detection from conversational telephone speech , 2012, Speech Commun..

[15]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[16]  Erik F. Tjong Kim Sang,et al.  Introduction to the CoNLL-2003 Shared Task: Language-Independent Named Entity Recognition , 2003, CoNLL.

[17]  Michiel Bacchiani,et al.  Restoring punctuation and capitalization in transcribed speech , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[18]  Gökhan Tür,et al.  Joint Discriminative Decoding of Words and Semantic Tags for Spoken Language Understanding , 2013, IEEE Transactions on Audio, Speech, and Language Processing.

[19]  Frédéric Béchet,et al.  Automatic transcription error recovery for Person Name Recognition , 2012, INTERSPEECH.

[20]  Erik F. Tjong Kim Sang,et al.  Introduction to the CoNLL-2002 Shared Task: Language-Independent Named Entity Recognition , 2002, CoNLL.

[21]  Denyse Baillargeon,et al.  Bibliographie , 1929 .

[22]  Pascale Fung,et al.  Using N-best lists for Named Entity Recognition from Chinese Speech , 2004, NAACL.

[23]  Ye-Yi Wang,et al.  Is word error rate a good indicator for spoken language understanding accuracy , 2003, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding (IEEE Cat. No.03EX721).

[24]  Frédéric Béchet,et al.  Robust Named Entity Extraction from Large Spoken Archives , 2005, HLT/EMNLP.

[25]  INPUTJi-Hwan Kim,et al.  A RULE-BASED NAMED ENTITY RECOGNITION SYSTEMFOR SPEECH , 2000 .

[26]  Frédéric Béchet,et al.  Unsupervised knowledge acquisition for Extracting Named Entities from speech , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[27]  Ji-Hwan Kim,et al.  A rule-based named entity recognition system for speech input , 2000, INTERSPEECH.

[28]  Guillaume Gravier,et al.  The ESTER phase II evaluation campaign for the rich transcription of French broadcast news , 2005, INTERSPEECH.

[29]  Sophie Rosset,et al.  Tree-Structured Named Entity Recognition on OCR Data: Analysis, Processing and Results , 2012, LREC.

[30]  Richard M. Schwartz,et al.  Named Entity Extraction from Noisy Input: Speech and OCR , 2000, ANLP.