Conversational search is a difficult task as it aims at retrieving documents based not only on
the current user query but also on the full conversation history. Most of the previous methods …

When users initiate search sessions, their query are often ambiguous or might lack of
context; this resulting in non-efficient document ranking. Multiple approaches have been …

Automated responses to questions for conversational agents, known as conversation
passage retrieval, is challenging due to omissions and implied context in user queries. To …

Most conversational passage retrieval systems try to resolve conversational dependencies
by using an intermediate query resolution step. To do so, they synthesize conversational …

Conversational search (CS) presents unique challenges, particularly context-awareness
and data limitation. This dissertation investigates these challenges and proposes novel …

The rise in popularity of mobile and voice search has led to a shift in IR from document to
passage retrieval for non-factoid questions. Various datasets such as MSMarco, as well as …

Team heatwave (of the University of Cambridge) submitted 3 automatic runs to the TREC
2022 Conversational Assistance Track. This paper discusses our approach to the challenge …

Conversational systems are increasingly becoming important gateways to information in a
wide range of application domains such as customer service, health, education, office work …

Large language models are now prevalent in the vast majority of research works such as
natural language processing, information retrieval, or computer vision. They have …

Les grands modèles de langue sont désormais prédominants dans la plupart des travaux de
recherche en traitement du langage naturel, en recherche d'information ou encore en vision …