t5-large-transferqa

We reproduced the TransferQA paper's QA pre-trained weights.

If you use this work for your research, please cite our work Dialogue Summaries as Dialogue States ({DS}2), Template-Guided Summarization for Few-shot Dialogue State Tracking

Citation

@inproceedings{shin-etal-2022-dialogue,
    title = "Dialogue Summaries as Dialogue States ({DS}2), Template-Guided Summarization for Few-shot Dialogue State Tracking",
    author = "Shin, Jamin  and
      Yu, Hangyeol  and
      Moon, Hyeongdon  and
      Madotto, Andrea  and
      Park, Juneyoung",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-acl.302",
    pages = "3824--3846",
    abstract = "Annotating task-oriented dialogues is notorious for the expensive and difficult data collection process. Few-shot dialogue state tracking (DST) is a realistic solution to this problem. In this paper, we hypothesize that dialogue summaries are essentially unstructured dialogue states; hence, we propose to reformulate dialogue state tracking as a dialogue summarization problem. To elaborate, we train a text-to-text language model with synthetic template-based dialogue summaries, generated by a set of rules from the dialogue states. Then, the dialogue states can be recovered by inversely applying the summary generation rules. We empirically show that our method DS2 outperforms previous works on few-shot DST in MultiWoZ 2.0 and 2.1, in both cross-domain and multi-domain settings. Our method also exhibits vast speedup during both training and inference as it can generate all states at once.Finally, based on our analysis, we discover that the naturalness of the summary templates plays a key role for successful training.",
}