About

MultiDoc2Dial is 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. 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 study, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains; and tasks that involve modeling the dialogue-based and document-based context for predicting the next agent turn. Figure 1 illustrates a goal-oriented dialogue that corresponds to multiple documents.

For more information, please refer to paper (Bibtex), code and leaderboard .

    @inproceedings{feng2021multidoc2dial,
      title={MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents},
      author={Feng, Song and Patel, Siva Sankalp and Wan, Hui and Joshi, Sachindra},
      booktitle={EMNLP},
      year={2021}
    }
  

Data

Please check out our data: data  and readme . For domain adapation set up, check out data  .