Annotation syntaxique automatique de la partie orale du ORFÉO (notice n° 697564)
[ vue normale ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02690cam a2200301 4500500 |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20250121212256.0 |
| 041 ## - LANGUAGE CODE | |
| Language code of text/sound track or separate title | fre |
| 042 ## - AUTHENTICATION CODE | |
| Authentication code | dc |
| 100 10 - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Nasr, Alexis |
| Relator term | author |
| 245 00 - TITLE STATEMENT | |
| Title | Annotation syntaxique automatique de la partie orale du ORFÉO |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Date of publication, distribution, etc. | 2020.<br/> |
| 500 ## - GENERAL NOTE | |
| General note | 55 |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Cet article présente les outils informatiques, développés dans le cadre du projet orféo, qui permettent de prédire de manière automatique les annotations linguistiques, en particulier les parties de discours, les lemmes, les dépendances syntaxiques et la segmentation des énoncés. Deux points importants sont mis en avant. Le premier est la segmentation en énoncés, qui est un problème difficile du traitement linguistique de l’oral. Nous montrons que la prise en compte de la syntaxe permet d’obtenir de bonnes performances de segmentation. Le second concerne la prise en compte de métadonnées dans les outils afin d’adapter ces derniers à la variété des données collectées. Les résultats obtenus sur le corpus de référence valident les approches proposées et permettent d’estimer la qualité des annotations produites automatiquement sur la portion du Corpus d’Étude pour le Français Contemporain ( céfc) non validée manuellement. |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Automatic syntactic parsing of the spoken part of the céfcThis paper presents the linguistic annotation tools that were developed in the framework of the orféo project and used to annotate the different corpora. Two important points are developed. The first one is sentence segmentation, which is a difficult problem when processing speech transcriptions. We show that taking into account syntax allows to obtain good segmentation performance. The second is the introduction of metadata features in the parsing process in order to adapt the models to the variety of data collected. The results obtained on the orféo corpus validate the proposed approaches and make it possible to estimate the quality of the annotations produced automatically on the orféo corpora which are not validated manually. |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | segmentation en énoncés |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | analyseur en transition |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | analyse syntaxique |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | analyse en dépendance |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | transition-based parser |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | dependency parsing |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | sentence segmentation |
| 690 ## - LOCAL SUBJECT ADDED ENTRY--TOPICAL TERM (OCLC, RLIN) | |
| Topical term or geographic name as entry element | syntactic parsing |
| 700 10 - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Dary, Franck |
| Relator term | author |
| 700 10 - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Béchet, Frédéric |
| Relator term | author |
| 700 10 - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Fabre, Benoît |
| Relator term | author |
| 786 0# - DATA SOURCE ENTRY | |
| Note | Langages | 219 | 3 | 2020-08-11 | p. 87-102 | 0458-726X |
| 856 41 - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="https://shs.cairn.info/revue-langages-2020-3-page-87?lang=fr&redirect-ssocas=7080">https://shs.cairn.info/revue-langages-2020-3-page-87?lang=fr&redirect-ssocas=7080</a> |
Pas d'exemplaire disponible.
Réseaux sociaux