1 code implementation • 31 Oct 2022 • Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Yanggang Wang, Haiyu Li, Zhilin Yang
Prompt-based techniques have demostrated great potential for improving the few-shot generalization of pretrained language models.
no code implementations • 18 Jan 2022 • Hanwei Xu, Yujun Chen, Yulun Du, Nan Shao, Yanggang Wang, Haiyu Li, Zhilin Yang
We propose a multitask pretraining approach ZeroPrompt for zero-shot generalization, focusing on task scaling and zero-shot prompting.
no code implementations • 7 Feb 2021 • Nan Shao, Yiming Cui, Ting Liu, Shijin Wang, Guoping Hu
To deal with this challenge, most of the existing works consider paragraphs as nodes in a graph and propose graph-based methods to retrieve them.
no code implementations • EMNLP 2020 • Nan Shao, Yiming Cui, Ting Liu, Shijin Wang, Guoping Hu
We construct a strong baseline model to establish that, with the proper use of pre-trained models, graph structure may not be necessary for multi-hop question answering.
no code implementations • CONLL 2019 • Wentao Ma, Yiming Cui, Nan Shao, Su He, Wei-Nan Zhang, Ting Liu, Shijin Wang, Guoping Hu
The heart of TripleNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels.