MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents

TL;DR

This paper introduces MultiDoc2Dial, a new dataset and task for modeling goal-oriented dialogues grounded in multiple documents across various domains, addressing more realistic multi-topic information-seeking scenarios.

Contribution

It presents a novel dataset and task for multi-document grounded dialogues, along with baseline models and experimental results to foster future research.

Findings

Baseline models demonstrate the feasibility of multi-document dialogue modeling.

Experimental results highlight challenges and potential directions for improvement.

The dataset covers four diverse domains for comprehensive evaluation.

Abstract

We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as a machine reading comprehension task based on a single given document or passage. In this work, we aim to address more realistic scenarios where a goal-oriented information-seeking conversation involves multiple topics, and hence is grounded on different documents. To facilitate such a task, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains. We also explore modeling the dialogue-based and document-based context in the dataset. We present strong baseline approaches and various experimental results, aiming to support further research efforts on such a task.