For many businesses, translation is a time-consuming, labor-intensive process. Human translators can take days to fully process, translate, and proof a few thousand words. Between sending jobs, communicating time frames and service prices, and receiving the actual translated document, businesses can spend several days waiting for a complete translation.
SYSTRAN’s Neural Machine Translation (NMT) solution cuts that process down to seconds. Our OpenNMT-powered neural engine and hyper-scalable architecture can almost instantly process translation requests. For example, it can translate a double-spaced, one-page Word document in around one second. NMT frees up human translators from grunt work and allows them to tackle more impactful, growth-oriented business problems.
Today, let’s discuss some of the features that allow us to provide those one-second, industry-leading turnaround times that facilitate nearly instant translations.
One of our Spring webinars featured Amy Ward, Product Marketing Specialist at Progress, Kamen Damyanov, Pre-Sales Solution Engineer at Progress, and Victor Ramirez, Director of Business Solutions at SYSTRAN. If you missed it, the group discussed the importance of technology in delivering superb customer experiences. Furthermore, the trio spoke about SYSTRAN’s collaboration with Sitefinity to introduce an innovative solution that facilitates a stronger global web presence.
As part of our webinar series, one of our latest broadcast discussed and demonstrated the unique and innovative Language I/O + SYSTRAN solution, created in collaboration with our partner company Language I/O.
Hosted by J. Obakhan from SYSTRAN and Heather Shoemaker, CEO of Language I/O, the webinar discussed the power of integrating machine language translation technology into the customer care workflow.
Our webinar “Get More From SPNS9” on May 15th, 2020 was a huge success. The webinar demonstrated 6 new exciting upgrades to the SYSTRAN Pure Neural Server 9.6’s, further scaling its technological capabilities. Thank you to those who joined us.
In this post, we have compiled the highlights from the presentation and answers to the questions we receive after.
The minds behind SYSTRAN sit down for an interview regarding the complexities and the capacities of specialized neural machine translation engines.
Participants: Peter Zoldan, Senior Data Engineer -Software Engineer Linguistic Program, Svetlana Zyrianova, Linguistic Program, Petra Bayrami, Jr. Software Engineer – Linguistic Program, Natalia Segal, R&D Engineer.
How much data is required to create a specialized engine?
The more bilingual data, the better the quality. For broad domains such as news, millions of bilingual sentences will be required. However, if the domain is narrow, such as technical support documents for certain products, then even a small set of sentences of 50,000, noticeably improves the quality.
The amount of data required will depend on how broad or narrow the domain is you are specializing the engine into.
Language is messy. Ask any person who has ever had to learn a second language and they will tell you that the most difficult aspect isn’t learning all the rules, but understanding the exceptions to the rules — the real-world application of the language.
e-Discovery can be a long, daunting process even in the best of times. In today’s globalized world of data, however, you not only have to worry about the sheer amount of information but also what language the content is in. This is where Neural Machine Translation comes in to break that language barrier. As fast as NMT is, though, odds are you have dreamed about how to make your systems even more efficient. How do you ensure any job can get completed on even the most ambitious of timelines?
SYSTRAN has been wholeheartedly involved in open source development over the past few years via the OpenNMT initiative,whose goal is to build a ready-to-use, fully inclusive, industry and research ready development framework for Neural Machine Translation (NMT). OpenNMT guarantees state-of-the-art systems to be integrated into SYSTRAN products and motivates us to continuously innovate.
In 2017, we published OpenNMT-tf, an open source toolkit for neural machine translation. This project is integrated into SYSTRAN’s model training architecture and plays a key role in the production of the 2nd generation of NMT engines.
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:
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.
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.
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.
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.
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.
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.
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.
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 the launch of a marketplace 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.