Doc2Bot: Accessing Heterogeneous Documents via Conversational Bots
This addresses the need for companies and organizations to manage large manuals via conversation, though it is incremental as it focuses on dataset creation and baseline tasks.
The paper tackles the problem of building conversational bots to access heterogeneous documents by introducing Doc2Bot, a dataset with over 100,000 turns from Chinese documents across five domains, which is larger than prior datasets and includes three challenging tasks for information seeking.
This paper introduces Doc2Bot, a novel dataset for building machines that help users seek information via conversations. This is of particular interest for companies and organizations that own a large number of manuals or instruction books. Despite its potential, the nature of our task poses several challenges: (1) documents contain various structures that hinder the ability of machines to comprehend, and (2) user information needs are often underspecified. Compared to prior datasets that either focus on a single structural type or overlook the role of questioning to uncover user needs, the Doc2Bot dataset is developed to target such challenges systematically. Our dataset contains over 100,000 turns based on Chinese documents from five domains, larger than any prior document-grounded dialog dataset for information seeking. We propose three tasks in Doc2Bot: (1) dialog state tracking to track user intentions, (2) dialog policy learning to plan system actions and contents, and (3) response generation which generates responses based on the outputs of the dialog policy. Baseline methods based on the latest deep learning models are presented, indicating that our proposed tasks are challenging and worthy of further research.