Work

What is Next when Sequential Prediction Meets Implicitly Hard Interaction?

Year: 2021

Type: conference-paper

Abstract: Hard interaction learning between source sequences and their next targets is challenging, which exists in a myriad of sequential prediction tasks. During the training process, most existing methods focus on explicitly hard interactions caused by wrong responses. However, a model might conduct correct responses by capturing a subset of learnable patterns, which results in implicitly hard interactions with some unlearned patterns. As such, its generalization performance is weakened. The problem gets more serious in sequential prediction due to the interference of substantial similar candidate targets.

Source: Proceedings of the ... ACM International Conference on Information & Knowledge Management

DOI: 10.1145/3459637.3482492

Authors: Kaixi Hu, Lin Li, Qing Xie, Jianquan Liu, Xiaohui Tao

Institutions: Wuhan University of Technology, NEC (Japan), University of Southern Queensland

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: China Scholarship Council

Awards: G2357583457, G3851277684