Chunyuan Li, Jianfeng Gao, Chenguang Zhu, Michael Zeng, Baolin Peng, Xiujun Li, Jinchao Li
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or statistical models typically relies on heavily annotated data, which is infeasible for new domains. Therefore, it is pivotal for an NLG system to generalize well with limited labelled data in real applications. To this end, we present FEWSHOTWOZ, the first NLG benchmark to simulate the few-shot learning setting in task-oriented dialog systems. Further, we develop the SC-GPT 1 model. It is pre-trained on a large set of annotated NLG corpus to acquire the controllable generation ability, and fine-tuned with only a few domain-specific labels to adapt to new domains. Experiments on FEWSHOTWOZ and the large Multi-Domain-WOZ datasets show that the proposed SC-GPT significantly outperforms existing methods, measured by various automatic metrics and human evaluations.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2002.12328")
get_code_for_paper("2002.12328")
have("2002.12328")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2002.12328.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2002.12328)
Connect an agent — have() is free.