In the last post, we spoke a bit about the different types of machine translation as well as their advantages and disadvantages. For this post, we delve a little deeper into one of the more exciting machine translation methods, Neural Machine Translation. As a quick recap, Neural Machine Translation is where deep neural networks are used to convert a sequence of words form the source language to a sequence of words to the target language. To accomplish this, Neural Machine Translations use neural networks to learn a statistical model for machine translation. Specifically, Neural Machine Translation uses an artificial neural network to predict a sequence of numbers when provided with a sequence of numbers. Simply put, words are encoded into numbers and then the numbers are input into a neural translation model and then outputs numbers which are then decoded into a translation.
How the neural network works and defines the inputted numbers to produce an output is perfected by training the network with millions of sentence pairs. So for example, if you are trying to train a Neural Machine Translation engine for English to Spanish, you would need to feed the engine a great deal of data to help tweak and refine its framework and make it more accurate. Each sentence pair that is given to the engine slightly modifies the neural network while it uses an algorithm called back-propagation. Back-propagation consists of fine-tuning the error rate that comes from the previous iteration. By properly tuning, the error rates can be reduced and the accuracy can be improved.
So what is the advantage of using Neural Machine Translation? Some of the biggest limitations of other machine translation is that they have difficulty when it comes to more complex or nuanced phrases. However, with Neural Machine Translation, it becomes much more possible to translate these kinds of phrases since the number of parameters and rules that can be given provided are much greater and therefore it is more possible to generate translations that are much more natural sounding and closer in meaning.
Neural Machine Translation is without doubt the future of Machine Translation, but there are still reasons as to why it is not widely being adopted. The biggest reason is the sheer cost and time sink that the engines require to actually become useful. As mentioned earlier, millions of sentences need to be entered into the engine for it to start to really output translations that can be considered good quality, and that means using more manpower and time. Not every company is able or willing to invest that many resources to develop a Neural Machine Translation engine, and that is perfectly understandable when weighing the cost versus the reward.
Overall, Neural Machine Translation is a complicated system, but has the most potential out of all of the Machine Translation methods. It is very possible that Neural Machine Translation will be developed to the point where it can accurately be used in a variety of situations for which it is specifically trained, but it is unknown when exactly that might happen. There have been many advancements in its development, but due to its cost and time consumption it will be quite some time before it will be able to be commonly used.