Wizard of Search Engine: Access to Information Through Conversations with Search Engines

TL;DR

This paper introduces a comprehensive pipeline, a benchmark dataset called WISE, and a neural architecture for conversational information seeking, enabling more systematic and effective research in this emerging area.

Contribution

It formulates a six-subtask pipeline for CIS, releases a new benchmark dataset, and designs a neural model with a pre-train/fine-tune scheme for improved performance.

Findings

The WISE dataset enables detailed CIS research.

The neural model achieves effective performance on CIS tasks.

Statistics reveal key characteristics of conversational information seeking.

Abstract

Conversational information seeking (CIS) is playing an increasingly important role in connecting people to information. Due to the lack of suitable resource, previous studies on CIS are limited to the study of theoretical/conceptual frameworks, laboratory-based user studies, or a particular aspect of CIS (e.g., asking clarifying questions). In this work, we make efforts to facilitate research on CIS from three aspects. (1) We formulate a pipeline for CIS with six sub-tasks: intent detection (ID), keyphrase extraction (KE), action prediction (AP), query selection (QS), passage selection (PS), and response generation (RG). (2) We release a benchmark dataset, called wizard of search engine (WISE), which allows for comprehensive and in-depth research on all aspects of CIS. (3) We design a neural architecture capable of training and evaluating both jointly and separately on the six sub-tasks, and devise a pre-train/fine-tune learning scheme, that can reduce the requirements of WISE in scale by making full use of available data. We report some useful characteristics of CIS based on statistics of WISE. We also show that our best performing model variant isable to achieve effective CIS as indicated by several metrics. We release the dataset, the code, as well as the evaluation scripts to facilitate future research by measuring further improvements in this important research direction.