MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents
This addresses a more realistic scenario for information-seeking conversations involving multiple topics, though it is incremental as it builds on existing document-grounded dialogue work.
The authors tackled the problem of modeling goal-oriented dialogues grounded in multiple documents, rather than a single one, by introducing the MultiDoc2Dial task and dataset across four domains, with strong baseline results provided.
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.