1. Paper title
Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations
2. link
https://www.aclweb.org/anthology/2020.acl-main.11.pdf
3. 摘要
We introduce Span-ConveRT, a light-weight model for dialog slot-filling which frames the task as a turn-based span extraction task. This formulation allows for a simple integration of conversational knowledge coded in large pretrained conversational models such as ConveRT (Henderson et al., 2019a). We show that leveraging such knowledge in Span-ConveRT is especially useful for few-shot learning scenarios: we report consistent gains over 1) a span extractor that trains representations from scratch in the target domain, and 2) a BERTbased span extractor. In order to inspire more work on span extraction for the slot-filling task, we also release RESTAURANTS-8K, a new challenging data set of 8,198 utterances, compiled from actual conversations in the restaurant booking domain.
4. 要解决什么问题
dialog slot-filling
[?] 没有搜到这种类型的Task
5. 作者的主要贡献
把dialog slot-filling变成了turn-based span extraction任务。
把对话知识集成到预训练的对话模型中。
[?] 没看懂
6. 得到了什么结果
对于 few shot场景，非常有用。
[?] 没看懂