Évaluation automatique de la satisfaction client à partir de conversations de type "chat" par réseaux de neurones récurrents avec mécanisme d’attention

Abstract : This paper presents methods to perform knowledge extraction from very large databases of WEB chat conversations between operators and clients in customer contact centers. Extracting knowledge from chat corpus is a challenging research issue. Simply applying traditional text mining tools is clearly sub-optimal as it takes into account neither the interaction dimension nor the particular nature of this language which shares properties of both spoken and written language. We present a method predicting users satisfaction in a chat-based service trained on answers from users to satisfaction surveys.
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01943265
Contributor : Jeremy Auguste <>
Submitted on : Monday, December 3, 2018 - 4:43:30 PM
Last modification on : Tuesday, April 16, 2019 - 1:41:20 AM
Document(s) archivé(s) le : Monday, March 4, 2019 - 2:54:30 PM

File

auguste_taln2018a.pdf
Explicit agreement for this submission

Identifiers

  • HAL Id : hal-01943265, version 1

Collections

Citation

Jeremy Auguste, Delphine Charlet, Géraldine Damnati, Benoit Favre, Frédéric Bechet. Évaluation automatique de la satisfaction client à partir de conversations de type "chat" par réseaux de neurones récurrents avec mécanisme d’attention. 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), 2018, Rennes, France. ⟨hal-01943265⟩

Share

Metrics

Record views

35

Files downloads

47