no code implementations • SIGIR 2021 • Xueying Zhang, Yunjiang Jiang, Yue Shang, Zhaomeng Cheng, Chi Zhang, Xiaochuan Fan, Yun Xiao, Bo Long
We propose a novel domain-specific generative pre-training (DS-GPT) method for text generation and apply it to the product titleand review summarization problems on E-commerce mobile display. First, we adopt a decoder-only transformer architecture, which fitswell for fine-tuning tasks by combining input and output all to-gether.
no code implementations • 13 Jan 2021 • Ziyang Liu, Zhaomeng Cheng, Yunjiang Jiang, Yue Shang, Wei Xiong, Sulong Xu, Bo Long, Di Jin
We propose in this paper a novel Second-order Relevance, which is fundamentally different from the previous First-order Relevance, to improve result relevance prediction.
no code implementations • 23 Oct 2020 • Di Jin, Xiangchen Song, Zhizhi Yu, Ziyang Liu, Heling Zhang, Zhaomeng Cheng, Jiawei Han
We propose BiTe-GCN, a novel GCN architecture with bidirectional convolution of both topology and features on text-rich networks to solve these limitations.