Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation

Wenxiang Jiao; Xing Wang; Zhaopeng Tu; Shuming Shi; Michael R. Lyu; Irwin King

doi:10.18653/v1/2021.acl-long.221

ScienceGate Book Chapters

JOURNAL ARTICLE

Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation

Wenxiang Jiao Xing Wang Zhaopeng Tu Shuming Shi Michael R. Lyu Irwin King

Year: 2021 Pages: 2840-2850

DOI: 10.18653/v1/2021.acl-long.221

Get Full-Text PDF Get Analytical Report

Abstract

Wenxiang Jiao, Xing Wang, Zhaopeng Tu, Shuming Shi, Michael Lyu, Irwin King. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Keywords:

Machine translation Computer science Natural language processing Artificial intelligence Computational linguistics Joint (building) Association (psychology) Sampling (signal processing) Training set Volume (thermodynamics) Artificial neural network Translation (biology) Speech recognition Linguistics Psychology Engineering Telecommunications Philosophy

Metrics

Cited By

3.25

FWCI (Field Weighted Citation Impact)

Refs

0.93

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Natural Language Processing Techniques

Physical Sciences → Computer Science → Artificial Intelligence

Topic Modeling

Physical Sciences → Computer Science → Artificial Intelligence

Multimodal Machine Learning Applications

Physical Sciences → Computer Science → Computer Vision and Pattern Recognition

Self-Training Sampling with Monolingual Data Uncertainty for Neural Machine Translation

Abstract

Metrics

Citation History

Topics

Related Documents

Effectively training neural machine translation models with monolingual data

Joint Training for Neural Machine Translation Models with Monolingual Data

Neural Machine Translation with Monolingual Translation Memory

Zero-Resource Neural Machine Translation with Monolingual Pivot Data

Exploiting Monolingual Data at Scale for Neural Machine Translation