Seven Tips for Better Translation Results

Whether you are using SYSTRAN’s Desktop, Enterprise Server, SaaS or online software, one question our IT Support is asked all the time is “How Can I Improve My Translation Output?” If incorrect or incomplete text or data is input into Machine Translation software, (also known as “garbage in, garbage out”) the outcome will, more often than not, also be incorrect or incomplete.

Here are seven tips to a better result:

  1. Use complete, grammatical sentences – Sentences should always start with a capital letter and end in either a period, exclamation point or question mark. A complete sentence always contains a verb, expresses an idea and makes sense standing alone.
  1. Avoid the passive voice – The passive voice is used to show interest in the person or object that experiences an action rather than the person or object that performs the action.
  1. Punctuation is important; clauses will translate best if separated by commas – Punctuation is the feature of writing that gives meaning to the written word. An error in punctuation can convey a completely different meaning to the one that is intended.
  1. Try to use simple, declarative sentences – A declarative sentence makes a statement, is in a present tense, and ends in a period. These are the most common sentences in the English language. It can either be a simple or compound sentence.
  1. Avoid ambiguity – To avoid ambiguity keep your sentences short, start with the subject, then the verb and end with the object. Use words and tenses consistently throughout.
  1. Avoid abbreviations, acronyms, jargon and colloquialisms – An abbreviation or acronym should first be spelled out if there are to be used consistently in a document. Colloquialisms are informal forms of speech and should be used mainly for speaking and not writing. Abbreviations, acronyms and jargon can be added to your User Dictionary or Translation Memories.
  1. Use your Dictionary Manager – SYSTRAN software includes a feature called the Dictionary Manager, which allows you to create your own dictionaries to supplement or override the main dictionary that comes with the program.  Using this feature can make substantial improvements to the translation.

The accuracy of the translation varies with the input.  If the input text is grammatically correct and unambiguous, it should translate well enough to convey the gist of what’s been written.

By: Ashley Shuler, Technical Support Analyst and Brooke Palm, Director of Customer Care SYSTRAN Software, Inc.

This was SYSTRAN Community Day’18!

Last week we hosted the 2018 edition of SYSTRAN Community Day! The conference was an exciting day full of energy, from Jean Senellart’s opening speech to our client success stories and celebrating SYSTRAN 50th anniversary! Here is a quick look at the conference highlights:

Jean Senellart announces SYSTRAN marketplace, a platform connecting the expertise of neural model trainers with the needs of industrial MT users

Jean Senellart, CEO of SYSTRAN France and CTO of the group opened the conference with a bold statement: the high quality of Neural Machine Translation has “commoditized” Machine Translation. As a commodity, NMT framework provides raw technology that needs to be refined, adapted and integrated for any industrial usage. After a look at the available NMT open source frameworks, including OpenNMT, cofounded and actively maintained by SYSTRAN, he made clear that streamlined training processes and data quality are the most crucial points to industrialize high quality neural machine translation.

Jean concluded his talk with the announcement of SYSTRAN marketplace, an open online platform where language experts have access to best of breed technology and framework to build, share, and sell language or domain models that can be accessed by industrial users. They will be able to select among hundreds of available models for any language pair and share feedback or evolution requests as per their specific needs.

Continue reading

SYSTRAN Demos Two New Integrations for Relativity at Ing3nious’ SoCal E-Discovery & Information Governance Retreat

This article was originally published on PR Newswire SYSTRAN Demos Two New Integrations for Relativity at Ing3nious’ SoCal E-Discovery & Information Governance Retreat

screen-shot-2016-11-16-at-1-54-07-pmSYSTRAN, a global leader in language translation technology, demonstrated two new integrations for SYSTRAN’s offering of Relativity at Ing3nious’ SoCal E-discovery & Information Governance Retreat, November 13-14.
SYSTRAN demonstrated two new integrations, aDiscovery and Anonymizer, for SYSTRAN’s offering of Relativity at the event. The aDiscovery feature will aid in audio discovery by transcribing audio files, detecting the source language and then translating the content. Anonymizer applies rigorous anonymization techniques to the full text and metadata of electronic documents within Relativity.

20161114_171147Anonymization can be used to mask identifying details in documents such as names, addresses, identification numbers, places, amounts and so forth when reading the anonymized documents; however, anonymized documents retain sufficient information for most relevancy reviews. Users also have the ability to “pseudononymize” selected names replacing pre-identified names with chosen pseudonyms on a mass basis to provide another option for privacy protection.

By 2020, Gartner predicts that 80 percent of litigation will involve multiple languages. The features are meant to assist with multi-language or cross-border e-discovery, giving legal teams a cost-effective method to translate files efficiently.

“These new integrations are going to change the way modern day legal teams handle multi-language files during e-discovery by maximizing productivity through automatic translation and Natural Language Processing (NLP),” says Ken Behan, SYSTRAN Vice President of Sales & Marketing. “These methods are far more efficient than manual translation and will save firms time and money during the e-discovery process.”

20161114_123107

In addition to the new integrations, SYSTRAN’s offering for Relativity automatically detects languages of files, translates documents that have multiple languages, and bulk translates using the Mass Action feature in Relativity. Organizations using Relativity are also able to support their billing process by accurately reflecting the workload completed.

To learn more about SYSTRAN’s offering of Relativity visit http://www.systransoft.com/translation-products/integrations/cmless-for-relativity.

About SYSTRAN

For over 48 years, SYSTRAN transformed the way global organizations such as Apple, Adobe, Daimler, HSBC, and Symantec meet the challenges of communicating globally via advanced machine-based translation technology. With the ability to facilitate communication in over 130 languages and 20 vertical domains, SYSTRAN enables instantaneous and automatic multilingual translations for texts, emails, chat, web pages, mobile apps, documents, user-generated content and more.

For more on SYSTRAN visit www.systrangroup.com

Related Links

SYSTRAN for Relativity – More Information

Related Video

 

This article was originally published on PR Newswire  SYSTRAN Demos Two New Integrations for Relativity at Ing3nious’ SoCal E-Discovery & Information Governance Retreat

State of the Union: The Next Generation of NLP

test1

In 1968, during the height of the Cold War, our nation’s intelligence organizations and military were working to decipher and understand Russian communication threads coming through their offices. Answering the call, SYSTRAN was born. We provided the vital translation software that our nation’s security forces required in order to do their job effectively.

Back then, we were providing our services through the IBM mainframe. Thankfully technology got smaller and more advanced, allowing SYSTRAN to move into several different areas. With the advent of the PC, we developed a product that people can use on the desktop, translating text into 130+ language combinations, enabling real-time multilingual communication across the globe.

Then recently, just in the last decade, we experienced further advancements through the smartphone. Speech recognition software along with the smartphone provided a plethora of breakthroughs. For example, SYSTRAN developed S-Translator, the official translation solution on the Samsung Galaxy S and Note series. Now if you’re in a taxi in Korea you can use your phone to tell someone where to go without speaking a word of the native language.

Continue reading

Cross Language Processing for 2016 Summer Olympics Content Generation

photo-1432753759888-b30b2bdac995 2

This summer, the social media sphere will be buzzing again with fans and athletes posting about the 2016 Summer Olympics in Rio de Janeiro, Brazil. It will be the first Olympic games to take place in South America. You can also expect networks, publishers, and brands to get in on the social media experience by generating more content than ever before.

Looking back to the London games in 2012, just the social media interactions on Twitter alone were vast in terms of engagement:

– On Twitter, there were 960K mentions for Bolt, 830K for Phelps, and 490K for Tom Daley (British diver who took the bronze) during the games.
– The first day of Olympics, there were 3 million tweets in total.

The numbers go on and on, especially when you take into account all the views, likes, tweets by sports teams, athletes, and brands. There are plenty of useful stats out there from archives of the first ever “Social Games” as most tech blogs described it.

Continue reading