Conversations with Documents. An Exploration of Document-Centered Assistance

TL;DR

This paper explores the potential of conversational assistants focused on document-centered tasks, including a survey of user needs, analysis of user queries, and initial machine learning models for question detection and answering.

Contribution

It provides a comprehensive survey of document-centered assistance, analyzes user query types, and introduces initial models for detecting and answering document-related questions.

Findings

Document-centered questions constitute the majority of user queries.

Initial models can accurately detect document-related questions.

Models show promise for effective document question answering.

Abstract

The role of conversational assistants has become more prevalent in helping people increase their productivity. Document-centered assistance, for example to help an individual quickly review a document, has seen less significant progress, even though it has the potential to tremendously increase a user's productivity. This type of document-centered assistance is the focus of this paper. Our contributions are three-fold: (1) We first present a survey to understand the space of document-centered assistance and the capabilities people expect in this scenario. (2) We investigate the types of queries that users will pose while seeking assistance with documents, and show that document-centered questions form the majority of these queries. (3) We present a set of initial machine learned models that show that (a) we can accurately detect document-centered questions, and (b) we can build reasonably accurate models for answering such questions. These positive results are encouraging, and suggest that even greater results may be attained with continued study of this interesting and novel problem space. Our findings have implications for the design of intelligent systems to support task completion via natural interactions with documents.