Research on Collaborative Machine English Translation Using the HIC Technology

Research on Collaborative Machine English Translation Using the HIC Technology

Jingjing Lv
Copyright: © 2022 |Pages: 15
DOI: 10.4018/IJISMD.300776
Article PDF Download
Open access articles are freely available for download

Abstract

Due to the rapid development of smart city, Hybrid Information Centric-Networking (HICN) emerges as a promising technology to enable the power of smart city. One of the most important application is the smart English translation, which becomes more and more popular with the process of Internationalization. In this work, we focus on studying the intelligent English translation is smart city using the HICN technology. Particularly, a method using collaborative machine learning and quality estimation technique is proposed, which sets a fixed threshold to filter pseudo-parallel data during unsupervised neural machine translation training. The quality estimation is used to evaluate and screen the pseudo-parallel data with high performance generated during reverse translation training. The results indicate that the proposed method outperforms the state-of-the-art methods.
Article Preview
Top

1. Introduction

The Information Centric-Networking (ICN) (Ion et al. 2013) is a novel and promising network architecture, which focuses on information and pays attention to the content itself. Instead, the location of the content storage is not the target. As the unique identification of the content, the content name is used for the positioning, routing and transmission of the content. Intra-network cache is one of the most important features of ICN network architecture (Kutscher et al. 2016). If the information requested by the user is matched in the router, the router sends the information directly to the user. Instead of parsing the address of the source host as in the traditional IP network, the source host must forward the message to the user, which greatly reduces the transmission delay and network traffic and improves the network performance (Eum et al. 2018). As you can see from figure 1, the biggest difference between ICN and the traditional TCP/IP model is that IP is replaced by Content Chunk at the “thin waist”, where the every node in the middle means the router or the switcher used to forward traffic from source to destination. From a network point of view, the naming of content is used instead of the naming of physical entities.In addition, the build-in storage function in the network is used to cache the passing data, to shorten the response time for other users to access the same data, and to greatly reduce the traffic in the network (Li et al. 2018).

Figure 1.

Comparison of protocol structures between traditional IP and ICN

IJISMD.300776.f01

ICN has been recognized by scientific research institutes and even some companies around the world (such as Cisco and Huawei) because of its unique characteristics of supporting on-net cache and IP address decoupling (Trossen et al. 2015). In order to speed up the process of ICN, many new networking modes, including data center network, software-defined network, mobile social network, satellite communication network and vehicle network, as well as cloud / fog / edge computing (Yi et al. 2021), 6G/5G, big data and network function virtualization are introduced to enhance ICN. This important integration with ICN is called the Hybrid ICN (HICN) (Muscariello et al. 2018). Although HICN has improved ICN to a great extent, it also faces some challenges that need to be solved urgently.

Now, smart city (Su et al. 2017), as an important application scenario of HICN, presents an important trend in the process of continuous research and development. It makes full use of the new generation of information technology in various industries in the city to create an advanced form of urban informatization based on the knowledge society (Neirotti et al. 2014). At the same time, with the development and acceleration of the process of internationalization, the popularization of English has become inevitable. Then, the combination of the two is the trend of the times, and it has become an important application of smart cities to accelerate and optimize English translation based on new information technology. Therefore, the intelligent English translation technology based on HICN has become the current research hotspot (Naeem et al. 2018).

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024)
Volume 14: 1 Issue (2023)
Volume 13: 8 Issues (2022): 7 Released, 1 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing