Andrea Madotto, Zhaojiang Lin, Zhou Yu, Bing Liu, Seungwhan Moon, Paul Crook, Zhiguang Wang, Zhenpeng Zhou, Eunjoon Cho, Rajen Subba
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach for zero-shot cross-domain DST. Specifically, our model first encodes dialogue context and slots with a pre-trained self-attentive encoder, and generates slot values in an auto-regressive manner. In addition, we incorporate Slot Type Informed Descriptions that capture the shared information across slots to facilitate cross-domain knowledge transfer. Experimental results on the MultiWOZ dataset show that our proposed method significantly improves existing stateof-the-art results in the zero-shot cross-domain setting.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2105.04222")
get_code_for_paper("2105.04222")
have("2105.04222")
Connect an agent — have() is free.