Skip to content
conftrace_
2019 ACL ACL 2019

Kingsoft’s Neural Machine Translation System for WMT19

Abstract

AbstractThis paper describes the Kingsoft AI Lab’s submission to the WMT2019 news translation shared task. We participated in two language directions: English-Chinese and Chinese-English. For both language directions, we trained several variants of Transformer models using the provided parallel data enlarged with a large quantity of back-translated monolingual data. The best translation result was obtained with ensemble and reranking techniques. According to automatic metrics (BLEU) our Chinese-English system reached the second highest score, and our English-Chinese system reached the second highest score for this subtask.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Xinze Guo, Chang Liu, Xiaolong Li, Yiran Wang, Guoliang Li, Feng Wang, Zhitao Xu, Liuyi Yang, Li Ma, Changliang Li

Topics

Deep Learning > Techniques > Model Architecture Natural Language Processing > Applications > Machine Translation Deep Learning > Learning Types > Ensemble Learning

Keywords

ensemble learning neural machine translation back translation transformer model
Download PDF

More from ACL 2019

All ACL 2019 papers →
The University of Sydney’s Machine Translation System for WMT19
UdS-DFKI Participation at WMT 2019: Low-Resource (en-gu) and Coreference-Aware (en-de) Systems
The IIIT-H Gujarati-English Machine Translation System for WMT19
The AFRL WMT19 Systems: Old Favorites and New Tricks
Evaluating the Supervised and Zero-shot Performance of Multi-lingual Translation Models
The MLLP-UPV Supervised Machine Translation Systems for WMT19 News Translation Task