Xueliang Zhao, Chongyang Tao, Rui Yan, Tingchen Fu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. We have no repository linked to it either. That is a statement about our graph, not about the paper.
Knowledge-grounded conversation (KGC) shows excellent potential to deliver an engaging and informative response. However, existing approaches emphasize selecting one golden knowledge given a particular dialogue context, overlooking the one-to-many phenomenon in dialogue. As a result, the existing paradigm limits the diversity of knowledge selection and generation. To this end, we establish a multireference KGC dataset and propose a series of metrics to systematically assess the one-tomany efficacy of existing KGC models. Furthermore, to extend the hypothesis space of knowledge selection to enhance the mapping relationship between multiple knowledge and multiple responses, we devise a span-based variational model and optimize the model in a wake-sleep style with an ameliorated evidence lower bound objective to learn the oneto-many generalization. Both automatic and human evaluations demonstrate the efficacy of our approach.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.12459")
get_code_for_paper("2210.12459")
have("2210.12459")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2210.12459.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2210.12459)
Connect an agent — have() is free.