| 
   
Machine Translation: Which Type Works Best?
by Donald A. DePalma
July 28, 2016
July 28, 2016

 
Download this research
Summary
Just a few years ago it seemed that the decade-old battle between rule-based and statistical machine translation had ended, with statistical approaches dominating and rule-based systems occupying a niche role in the industry. Hybrid technology that combines the two was becoming more common. However, MT is a constantly developing field, and since 2010, new entrants and methods have created more options.  In this brief we review the state of the various approaches currently in production or on the horizon. It discusses rule-based, statistical, hybrid, sub-segment, and neural net MT, compares them, and outlines deployment choices. 

Note: This brief replaces "Rules-Based, Statististical, or Hybrid: Which MT Is Best?" (Oct11). It updates the discussion of the various MT models, reflects changes in the supplier landscape, and adds discussions of solutions based on sub- segment and neural net technology. 

This report has been replaced by “Machine Translation: Which Type Works Best? (2018),” published on June 28, 2018. The newer version reflects major developments in the machine translation market that have occurred since this report was published. This version is preserved for historical reference.

Availability
  • Global Leaders
  • Industry Providers
  • Technology Vendors

Pages: 11
 

Related research
Find similar research by  
More

 
 
 
Terms of Use | Privacy Statement | Contact Us
Copyright © 2018 Common Sense Advisory, Inc. All Rights Reserved.