Towards a Model for Spoken Conversational Search

TL;DR

This paper explores the foundational aspects of spoken conversational search (SCS), analyzing conversational actions and proposing a schema to enhance interactivity and pro-activity in audio-based information retrieval systems.

Contribution

It introduces the first annotation schema for SCS, develops a dataset, and highlights the importance of discourse integration for effective spoken search models.

Findings

SCS requires interactivity and pro-activity to handle audio-only search complexity

Developed the SCSdata dataset and the SCoSAS annotation schema

Emphasized the need for discourse integration in SCS models

Abstract

Conversation is the natural mode for information exchange in daily life, a spoken conversational interaction for search input and output is a logical format for information seeking. However, the conceptualisation of user-system interactions or information exchange in spoken conversational search (SCS) has not been explored. The first step in conceptualising SCS is to understand the conversational moves used in an audio-only communication channel for search. This paper explores conversational actions for the task of search. We define a qualitative methodology for creating conversational datasets, propose analysis protocols, and develop the SCSdata. Furthermore, we use the SCSdata to create the first annotation schema for SCS: the SCoSAS, enabling us to investigate interactivity in SCS. We further establish that SCS needs to incorporate interactivity and pro-activity to overcome the complexity that the information seeking process in an audio-only channel poses. In summary, this exploratory study unpacks the breadth of SCS. Our results highlight the need for integrating discourse in future SCS models and contributes the advancement in the formalisation of SCS models and the design of SCS systems.