activity
20172022
most citedAcquiring Knowledge from Pre-trained Model to Neural Machine Translation

11 citations · 39 across the 7 of their papers we have counts for

collaborators

12 papers

cs.CL2022

Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation

Xiangpeng Wei, Heng Yu, Yue Hu +4

The principal task in supervised neural machine translation (NMT) is to learn to generate target sentences conditioned on the source inputs from a set of parallel sentence pairs, a…

cs.CL2020

Uncertainty-Aware Semantic Augmentation for Neural Machine Translation

Xiangpeng Wei, Heng Yu, Yue Hu +3

As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid cou…

cs.CL2020

On Learning Universal Representations Across Languages

Xiangpeng Wei, Rongxiang Weng, Yue Hu +3

Recent studies have demonstrated the overwhelming advantage of cross-lingual pre-trained models (PTMs), such as multilingual BERT and XLM, on cross-lingual NLP tasks. However, exis…

cs.CL20207 cited

Multiscale Collaborative Deep Models for Neural Machine Translation

Xiangpeng Wei, Heng Yu, Yue Hu +3

Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train. In this paper, we present a Multi…

cs.CL20204 cited

AR: Auto-Repair the Synthetic Data for Neural Machine Translation

Shanbo Cheng, Shaohui Kuang, Rongxiang Weng +3

Compared with only using limited authentic parallel data as training corpus, many studies have proved that incorporating synthetic parallel data, which generated by back translatio…

cs.CL2020

GRET: Global Representation Enhanced Transformer

Rongxiang Weng, Haoran Wei, Shujian Huang +4

Transformer, based on the encoder-decoder framework, has achieved state-of-the-art performance on several natural language generation tasks. The encoder maps the words in the input…