Role of Attentive History Selection in Conversational Information Seeking

TL;DR

This paper introduces an attention-based method for dynamically selecting and weighing conversational history in retrieval tasks, improving the relevance of retrieved documents in conversational search systems.

Contribution

It proposes a novel soft attention mechanism for history selection in open-retrieval conversational search, moving beyond simple concatenation of recent turns.

Findings

Attention-based history selection improves retrieval relevance.

Dynamic weighing of history turns outperforms fixed window approaches.

The method is effective in open-retrieval settings with large document collections.

Abstract

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.