no code implementations • 1 Jan 2021 • Fengshun Xiao, Zuchao Li, Hai Zhao
In neural machine translation (NMT), data augmentation methods such as back-translation make it possible to use extra monolingual data to help improve translation performance, while it needs extra training data and the in-domain monolingual data is not always available.
1 code implementation • 6 Nov 2019 • Ying Luo, Fengshun Xiao, Hai Zhao
In this paper, we address these two deficiencies and propose a model augmented with hierarchical contextualized representation: sentence-level representation and document-level representation.
Ranked #13 on Named Entity Recognition (NER) on Ontonotes v5 (English) (using extra training data)
no code implementations • 22 Aug 2019 • Zuchao Li, Hai Zhao, Yingting Wu, Fengshun Xiao, Shu Jiang
Our experiments indicate that switching to the DSD loss after the convergence of ML training helps models escape local optima and stimulates stable performance improvements.
no code implementations • ACL 2019 • Fengshun Xiao, Jiangtong Li, Hai Zhao, Rui Wang, Kehai Chen
To integrate different segmentations with the state-of-the-art NMT model, Transformer, we propose lattice-based encoders to explore effective word or subword representation in an automatic way during training.