SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04222 · NAACL · 2021

Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking

Andrea Madotto, Zhaojiang Lin, Zhou Yu, Bing Liu, Seungwhan Moon, Paul Crook, Zhiguang Wang, Zhenpeng Zhou, Eunjoon Cho, Rajen Subba

arXiv · PDF · Open in the Atlas

Code that ran

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.

Abstract

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.

For agents

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.