no code implementations • AACL (NLP-TEA) 2020 • Deng Liang, Chen Zheng, Lei Guo, Xin Cui, Xiuzhang Xiong, Hengqiao Rong, Jinpeng Dong
This paper presents the UNIPUS-Flaubert team’s hybrid system for the NLPTEA 2020 shared task of Chinese Grammatical Error Diagnosis (CGED).
1 code implementation • Findings (ACL) 2021 • Pei Ke, Haozhe Ji, Yu Ran, Xin Cui, LiWei Wang, Linfeng Song, Xiaoyan Zhu, Minlie Huang
Existing pre-trained models for knowledge-graph-to-text (KG-to-text) generation simply fine-tune text-to-text pre-trained models such as BART or T5 on KG-to-text datasets, which largely ignore the graph structure during encoding and lack elaborate pre-training tasks to explicitly model graph-text alignments.
Ranked #1 on KG-to-Text Generation on WebQuestions
no code implementations • 13 Sep 2019 • Yadong Li, Xin Cui
Our method is based on an accurate analytical approximation to the Shapley value of a neuron with ReLU activation.