Machine Translation : The Neural Frontier

Machine Translation : The Neural Frontier

This week we are treating you to an abridged version of an article written by Iconic CEO John Tinsley which features in this month’s edition of Multilingual magazine. As the intrigue surrounding Neural Machine Translation gathers apace, John shares his thoughts on The Neural Frontier…

nmtNeural Machine Translation (NMT) is a topic that is on everyone’s lips these days.

While technical details are comprehensive and easily found (if not as easily understandable) there hasn’t been a lot of discussion about the impact of this technology on the translation and localization industry from a practical perspective. In the absence of such discussion, there has been a lot of hype surrounding Neural MT, much of which has been taken out of context.

Although it is clear that we are at the peak of a hype cycle when it comes to Neural MT, there is justifiable cause for the optimism. In order to understand what exactly the fuss is all about, we need to take a brief look back at the history of MT research and development to see where exactly it fits in context.

In the early 1990’s we had our first paradigm shift from rule-based to statistical MT when researchers applied purely statistical, data-driven approaches to the task of translation. While initially met with scepticism, this quickly became the state of the art and has been the approach that researchers and developers have been building upon for the last 20 years…until now.

NMT Graph 2 a

The excitement surrounding NMT stems from the fact that this is another paradigm shift in how we do machine translation. While we are still in the very early days of this paradigm and need to realize that we don’t have a silver bullet on our hands, which in itself is exciting. With Neural MT, we have a blank canvas and our starting point is already quite strong in terms of quality. That’s what is exciting.

Is it really that good?

Despite the fact that we are in the early days of Neural MT, there is clearly cause for optimism based on initial performance. Neural MT can be very good insofar as the results are comparable to, if not better than existing approaches to MT in many cases. With languages that have traditionally proved harder for MT – such as Japanese, Korean, and Arabic – Neural MT is showing very promising results. These languages have the common trait that they are grammatically complex, and highly inflected, amongst other things, and the neural networks are doing a good job at generalizing over these issues to generate more accurate, fluent output.

On the other hand, for languages that are “easier” for MT and where existing approaches can already perform to a very high level, the improvements seen by Neural MT are much less stark, if there at all. It is the case that, for languages where there is a lot of room for improvement, Neural MT has the room to improve. But the higher the initial quality bar, the lesser the impact Neural MT is having at this point in time.

These assessments have also highlighted areas where Neural MT still needs work, and perhaps falls down where existing MT is strong, particularly as relates to the handling of unknown words and the application of terminology. Assessments to date have been academic in nature meaning they’ve been focused on gathering broad findings on general data. Whether these results will hold for specific industry use cases or on “real” data remains to be seen.

What does the neural frontier look like?

The biggest impact that Neural MT will have in the short-term – on the languages for which it has been developed and where it has shown to perform well – is that it’s going to raise the bar for the effectiveness of general purpose MT.

Things will get really interesting over the next 2 to 5 years as we gain much more clarity into the ‘how’ and ‘why’ of Neural MT. We will begin to see new types of hybrid MT that include neural approaches. When statistical MT emerged, rule-based MT didn’t go away. The technologies ran in parallel, and still do in many cases. The same will happen with Neural MT. We have already seen researchers working on neural post-editing of statistical MT output, and this trend of hybrid engines, and system combination will continue.

MT and the legal industry

We’re already seeing trends towards new use cases for machine translation, aside from the “traditional” post-editing workflow. These frequently include cases where we have large volumes of content that need to be turned around quickly, such as e-discovery and cross-border litigation.

Similarly, use cases that require real-time translation and translation that is fit for a particular purpose are emerging as prime candidates for MT, including multilingual customer support, e-commerce, and content that is created in a continuous delivery environment. These trends will continue upward as Neural MT comes on-stream in the medium term.

Longer term, it’s obviously difficult to predict the future but there is one thing we can say for certain – Neural MT will not be a replacement for human/professional/manual translation. It’s not a case of human vs. machine, or which is “better”. They are complementary approaches. Although Machine Translation can be used to aid the overall translation process, be it as segments for post-editing, to provide terminology suggestions, or to help determine which specific documents from large batches require full translation.

On the other hand, there are cases where Machine Translation is the most appropriate solution, or the only option. This can include cases where instant translation is required in real-time, or massive volumes of content needs to be translated in a short space of time. These also include cases where only a gist translation is needed, and perhaps doesn’t justify the cost or time needed for a human translation.

Similarly, human translation is not going away! In a sense, it feels very obvious to spell it out but given some of the reporting on Neural MT it also feels very necessary.   When dealing with mission critical tasks, particularly challenging languages or content types, and, importantly, cases where fully fluent and adequate translations need to be guaranteed, we will always take the human translation approach.

Cautious Optimism

This first generation of Neural MT solutions are only general-purpose systems, but they are clearly showing great promise and, in many cases, improvements over existing technology, for the general use case. While we need to be cautious in terms over-blowing the potential of Neural MT, and particularly the time frame in which that potential might be realized, there is without doubt great cause for optimism.

Here at Iconic we are excited to be incorporating Neural MT in cases where it can provide a real benefit. Check out our presentation below detailing some recent case studies!

About Iconic Translation Machines

Iconic Translation Machines is a leading machine translation software and solutions provider who specialise in custom solutions tailored with subject matter expertise for specific industry sectors including eDiscovery, legal, life sciences, and financial services. Iconic is the MT partner of choice for some of the world’s largest translation companies, information providers, and government and enterprise organisations, helping them to translate more content, more accurately and in less time, resulting in significant cost savings and increased revenue. Iconic is based in Dublin, Ireland.

Thank you, your sign-up request was successful! Please check your e-mail inbox.
That email address is already subscribed, thank you!
Please provide a valid email address.
Oops. Something went wrong. Please try again later.


Comments are closed.

Get Started