OpenNMT-tf 2.0: a milestone in the OpenNMT project

OpenNMT-tf 2.0 workshop. Red Kakemonos and French Tech Central logo in front of the entrance door of Station F held in Paris in March 2018.
OpenNMT workshop held in March 2018 at Station F in Paris // Copyright SYSTRAN

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.

Continue reading

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.

F.A.Q photo with tagline "How can i impove my translation output?" - SYSTRAN is showing ways to make better translation.

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 the launch of a marketplace connecting the expertise of neural model trainers with the needs of industrial MT users

Full room for Jean Senellart conference at SYSTRAN Community Day, took place on November 8th at the Cloud Business Center in Paris

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 presents its latest translation engines: huge quality & speed improvement!

Logo of SYSTRAN Pure Neural Server technology, a huge gap in AI quality & speed improvement for translation

The latest version of our AI-powered Translation Software designed for Businesses

SYSTRAN Pure Neural® Server is our new generation of enterprise translation software based on Artificial Intelligence and Neural networks. It provides outstanding professional quality with the highest standards in data safety.

Our R&D team, extremely active to provide corporate users with state-of-the-art translation technology tailored for business, just released a new generation of Neural MT engines. SYSTRAN new engines are developed with OpenNMT-tf, our AI framework using latest TensorFlow features, and backed by a proprietary new training process: Infinite Training.

Continue reading

Open Source, Multilingual AI and Artificial Neural Networks : The new Holy Grail for the GAFA

Jean Senellart, CTO & CEO of SYSTRAN is explaining how SYSTRAN represent a GAFA alternative when they took benefit from Open Source, Multilingual AI and Artificial Neural Networks. Since 2016, there has been a sharp increase in open source machine translation projects based on neural networks or Neural Machine Translation (NMT) led by companies such as Google, Facebook and SYSTRAN. Why have machine translation and NMT-related innovations become the new Holy Grail for tech companies? And does the future of these companies rely on machine translation?

Never before has a technological field undergone so much disruption in such a short time. Invented in the 1960s, machine translation was first based on grammatical and syntactical rules until 2007. Statistical modelling (known as statistical translation or SMT), which matured particularly due to the abundance of data, then took over. Although statistical translation was introduced by IBM in the 1990s, it took 15 years for the technology to reach mass adoption. Neural Machine Translation on the other hand, only took two years to be widely adopted by the industry after being introduced by academia in 2014, showing the acceleration of innovation in this field. Machine translation is currently experiencing a golden age of technology.

From Big Data to Good Data

Not only have these successive waves of technology differed in their pace of development and adoption, but their key strengths or “core values” have also changed. In rule-based translation, value was brought by code and accumulated linguistic resources. For statistical models, the amount of data was paramount. The more data you had, the better the quality of your translation and your evaluation via the BLEU score (Bilingual Evaluation Understudy, the most widely used algorithm measuring machine translation quality). Now, the move to Machine translation based on neural networks and Deep Learning is well underway and has brought about major changes. The engines are trained to learn language as a child does, progressing step by step. The challenge is not only to process exponential data (Big Data) but more importantly to feed the engines the most qualitative data possible. Hence the interest in “Good data.”

Continue reading

SYSTRAN Celebrates 50 Years in Business

SYSTRAN 50th anniversary celebration logo. "50th anniversary" terms has a yellow background.

SYSTRAN celebrates its golden anniversary as a machine translation company by looking back at their most memorable milestones.

In the last 50 years, SYSTRAN has had the great pleasure of delivering machine translation capabilities to the Fortune 500, unicorn start-ups, education institutions, non-profits, government communities and LSPs worldwide. They’ve arrived at a unique vantage point across industries such as banking, finance, manufacturing, legal, internet, security, software, wearable devices and IoT.

“To have experienced decades of SYSTRAN’s impact on technology and culture has been a gift,” says Denis A. Gachot, CEO of SYSTRAN Software Inc. “However, what I find more inspiring is the intention of our founder Peter Toma when starting SYSTRAN.”

“I felt deeply that I had to devote my energy to the elimination of world conflict causing factors. As a first step to overcome the language problem, I felt that I should know as many languages as possible and use technology so others could be understood.” – Peter Toma

From powering the translation that helped the U.S. and Soviet astronauts communicate, bringing on-line translation to the internet and assisting the F500 corporations to collaborate globally, these moments not only commemorate their longevity, but they also show their values.

Commenting on reaching 50, Chairman Mr. Chang-Jin Ji believes that SYSTRAN would not be celebrating today if it was not for the dedication of employees around the globe to customer support and innovation. “I truly thank them and the loyal support we have received from our customers.”

Looking to the future, this month SYSTRAN will launch a new generation of their server solution, SYSTRAN Pure Neural® Server, that pushes the quality and fluency boundary further than ever before explains Jean Senellart, Global CTO of SYSTRAN. “This new release benefits from the state-of-the-art research in neural translation and brings to our customers these technologies for their specialized models in a fully integrated solution. Our commitment to Open Source through the OpenNMT project, now comprising more than 1,600 members, has been pushing our development teams to achieve excellence, and is raising the bar for the whole industry.”

See SYSTRAN’s most memorable moments in this commemorative video.

Contact: | Craig Stern | Director of Marketing | craig.stern@systrangroup.com

Innovation & Security for Critical Manufacturing: MANUSEC Summit in Munich, we’ll be there!

Porter of the event MANUSEC focuses on Cyber Security for Critical Manufacturing. There you can see a crane and a padlock

To start off 2018 right, we are participating in our first event of the year: The MANUSEC 2018 as an official sponsor.

The two-day event will take place on February 7th8th 2018 in Munich and will mainly focus on the innovations and advancements being made in Cyber Security for the manufacturing industry.

We therefore invite you to join us and attend our speaker session on February 7th at 11:50 AM UTC+1: “Keep your translated data safe by using a secure and tailored solution based on the latest AI innovations”

Our account manager Loïc RENE, in charge of the manufacturing and automotive industry will be your main contact there. Please feel free to get in touch with him before or during the event to arrange a meeting onsite.

We cannot wait to meet you there! Benefit from 25% off with the code SYSTRAN25 at online registration.

Continue reading

Artificial Intelligence: And You, How Will You Raise Your AI?

Picture and quote of Jean Senellart, Global CTO of SYSTRAN. Talks about AI, data and technology.

[This article originally appeared on Kirti Vashee’s Blog]

This is the final post for the 2017 year, a guest post by Jean Senellart who has been a serious MT practitioner for around 40 years, with deep expertise in all the technology paradigms that have been used to do machine translation. SYSTRAN has recently been running tests building MT systems with different datasets and parameters to evaluate how data and parameter variation affect MT output quality. As Jean said:

” We are continuously feeding data to a collection of models with different parameters – and at each iteration, we change the parameters. We have systems that are being evaluated in this setup for about 2 months and we see that they continue to learn.”

This is more of a vision statement about the future evolution of this (MT) technology, where they continue to learn and improve, rather than a direct reporting of experimental results, and I think is a fitting way to end the year in this blog.

It is very clear to most of us that deep learning based approaches are the way forward for continued MT technology evolution. However, skill with this technology will come with experimentation and understanding of data quality and control parameters. Babies learn by exploration and experimentation, and maybe we need to approach our continued learning, in the same way, learning from purposeful play. Is this not the way that intelligence evolves? Many experts say that AI is going to be driving learning and evolution in business practices in almost every sphere of business.

Continue reading

Return on expertise: Alvarez & Marsal reveal the backstage of eDiscovery success stories with SYSTRAN Pure Neural™ Machine Translation

SYSTRAN’s solution are used every day by various types of companies across many industries to get the most accurate and secure automatic translations on any type of content – from sensitive documents to websites to mobile apps and much more.  We’d like to focus today on how one of our clients – Alvarez & Marsal, a consultancy firm- uses SYSTRAN’s platform to manage eDiscovery projects with the highest efficiency and accuracy.

The processes and tools used in eDiscovery scenarios are, most of the time, quite complex given the large volumes of electronic data produced. Unlike hard-copy evidence, e-documents are a lot more dynamic and contain various metadata that demand the highest translation quality in order to eliminate any claims of spoliation at any time in a litigation case.

Phil Beckett, the firm’s Managing Director, who has recently been named ‘Investigation Digital Forensic Expert of the year’ by Who’s Who Legal is talking to us about how SYSTRAN’s solutions plug into their internal processes to manage their projects end to end.

Phil Beckett – Managing Director at Alvarez & Marsal

Continue reading

The use of machine translation in eDiscovery

Quote

Professional is working on a laptop and writing something on a sheet. SYSTRAN's & A&M logos are below the picture. The use of Machine Translation in eDiscovery is the tagline.

This article originally appeared on Kirti Vashee’s Blog.

There are some kinds of translation applications where MT just makes sense, and it would be foolish to even attempt these kinds of projects without decent MT technology as a foundation. Usually, this is because these applications have some combination of the following factors:

  • Very large volume of source content that simply could NOT be translated without MT in any useful time frame
  • Rapid turnaround requirement (days, hours or minutes) for the content to have any value to the translation consumers
  • A user tolerance for lower quality translations at least in early stages of information review
  • To enable information and document triage when dealing with large document collections and help to identify highest priority content from a large mass of undifferentiated content. This process also helps to identify the most important and relevant documents to send to higher quality human translation.
  • Translation Cost prohibitions (usually related to volume)

Continue reading