Une archive numérique francophone des articles de recherche en Traitement Automatique de la Langue.

Review of neural automatic summarization of conversations for a medical chatbot

Jessica Lopez

Abstract : Conversational analysis plays an important role in the development of simulation devices for the training of health professionals (doctors, nurses). Our goal is to develop an original automatic synthesis method for medical conversations between a patient and a healthcare professional, based on recent advances in summarization using convolutional and recurrent neural networks. The proposed method must be adapted to the specific problems related to the synthesis of dialogues. This article presents a review of the different methods for extractive and abstractive summarization, and for dialogue analysis. We also describe the use of Natural Language Processing in the medical field.

Keywords : Automatic summarization, medical domain, dialogues, review.