Role of Attentive History Selection in Conversational Information Seeking
This work tackles the problem of effectively utilizing conversational history for improved information retrieval in intelligent assistant systems, which is an incremental improvement for the IR community.
This paper addresses the challenge of incorporating conversational history into information retrieval systems for conversational search. The authors propose a dynamic history selection method using an attention mechanism to weigh and select relevant past turns, aiming to improve question embedding for retrieval.
The rise of intelligent assistant systems like Siri and Alexa have led to the emergence of Conversational Search, a research track of Information Retrieval (IR) that involves interactive and iterative information-seeking user-system dialog. Recently released OR-QuAC and TCAsT19 datasets narrow their research focus on the retrieval aspect of conversational search i.e. fetching the relevant documents (passages) from a large collection using the conversational search history. Currently proposed models for these datasets incorporate history in retrieval by appending the last N turns to the current question before encoding. We propose to use another history selection approach that dynamically selects and weighs history turns using the attention mechanism for question embedding. The novelty of our approach lies in experimenting with soft attention-based history selection approach in an open-retrieval setting.