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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.18653/v1/2021.emnlp-main.498 | EMNLP |
DocType | Volume | ISSN |
Conference | 2021.emnlp-main | Proceedings of the 2021 Conference on Empirical Methods in Natural
Language Processing |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Song Feng | 1 | 280 | 19.55 |
Siva Sankalp Patel | 2 | 0 | 0.34 |
Hui Wan | 3 | 1 | 1.39 |
Sachindra Joshi | 4 | 221 | 25.75 |