• No results found

Supervised neural machine translation based on data augmentation and improved training & inference process

N/A
N/A
Protected

Academic year: 2020

Share "Supervised neural machine translation based on data augmentation and improved training & inference process"

Copied!
5
0
0

Loading.... (view fulltext now)

Full text

Loading

Figure

Table 1: Results of subtasks
Table 5: Technical point contributions

References

Related documents

We investigate adaptive ensemble weighting for Neural Machine Translation, addressing the case of improving performance on a new and potentially unknown domain without sac-

We present the NRC submission to the WMT19 Kazakh-English news translation shared task. Our submitted system is a multi-source, multi-encoder neural machine translation system

In this dissertation, we have presented a novel approach to learn code transformations via Neural Machine Translation in the context of three major software engineering tasks:

On English→French and English→German translation tasks, we observed that the neural machine translation models trained using the proposed method performed as well as, or better

This paper describes the submission of the NiuTrans neural machine translation sys- tem for the WMT 2018 Chinese ↔ En- glish news translation tasks.. Our baseline systems are based

Denois- ing neural machine translation training with trusted data and online data selection..

In this work we explored the use of rule-based machine translation (RBMT) knowledge to im- prove the performance of neural machine transla- tion (NMT) models in an

Extending Neural Machine Translation to Documents and Signed Languages Kayo Yin Talk @ University of Pittsburgh October 7 2021... Neural Machine Translation is the state-of-the-art