Catégorie
Other seminars
Séminaire | Adapting Semantic Textual Similarity and Conversational Question Answering approaches for Dialogue Systems
Bandeau image
![](/sites/default/files/2020-01/Bandeau%20Bleu_0.png)
Chapo
Jon Ander Campos, doctorant à l'université du Pays Basque et stagiaire au LIMSI, présentera ses travaux lors d'un séminaire.
Contenu
Corps de texte
Le groupe ILES a accueilli Jon Ander Campos doctorant à l'université du Pays Basque pour un stage doctoral de 3 mois. Son stage a été financé par l’appel à projet DATAIA. Son stage s'achevant fin janvier, Jon Ander nous présentera ses travaux.
Dialogue systems have been widely studied by the NLP community in the last decades. This kind of systems generally consist of three main modules: natural language understanding, dialogue manager and natural language generation. Lately, motivated by machine comprehension, conversational QA has emerged as a intermediate task between QA and dialogue, where machines have to assist users in information gathering by conversational means.
In this work, we merge traditional dialogue systems and conversational QA models for task oriented dialogues in the cooking domain. STS and IR systems are used as an intermediate layer between the dialogue system and the ConvQA model, where the impact of simple dialogue history modeling is also analyzed.