TechGist05

This is the second post in our posts series on machine translation quality. Again this is a slightly less polished and raw variant of a version published on the SDL site . The first one focused on BLEU scores , which are often improperly used to make decisions on inferred MT quality, where it clearly is not the best metric to draw this inference. The reality of many of these comparisons today is that scores based on publicly available (i.e. not blind) news domain tests are being used by many companies and LSPs to select MT systems which translate IT, customer support, pharma, financial services domain related content. Clearly, this can only result in sub-optimal choices. The use of machine translation (MT) in the translation industry has historically been heavily focused on localization use cases, with the primary intention to improve efficiency, that is, speed up turnaround and reduce unit word cost. Indeed, machine translation post-editing (MTPE) has been instrumental in helping loca...

This is the first in a series of posts discussing various aspects of MT quality from the context of enterprise use and value, where linguistic quality is important, but not the only determinant of suitability in a structured MT technology evaluation process. A cleaner, more polished, and shorter studio version of this post is available here . You can consider this post a first draft, or the live stage performance (stream of consciousness) version. What is BLEU (Bilingual Evaluation Understudy)? As the use of enterprise machine translation expands, it becomes increasingly more important for users and practitioners to understand MT quality issues in a relevant, meaningful, and accurate way. The BLEU score is a string-matching algorithm that provides basic output quality metrics for MT researchers and developers . In this first post, we will review and look more closely at the  BLEU score , which is probably the most widely used MT quality assessment metric in use by MT researchers an...

This is a guest post by Luigi Muzii that focuses mostly on the various questions that surround Language Data, which by most “big data” definitions and volumes is really not what most in the community would consider big data. As the world hurtles into the brave new world that is being created by a growling volume of machine learning and AI applications, the question of getting the data right is often brushed aside. Most think the data is a solved problem or presume that data is easily available. However, those of us who have been working at MT seriously over the last decade understand this is far from a solved problem. Machines learn from data and smart engineers can find ways to leverage the patterns in data in innumerable ways. Properly used it can make knowledge work easier, or more efficient e.g. machine translation, recommendation, and personalization. The value and quality of this pattern learning can only be as good as the data used, and however exciting all this technology seem...

Happy New Year This is yet another post on Blockchain, a guest post by Robert Etches who presents his vision of what Blockchain might be able to be in the translation industry. A vision, by definition, implies a series of possibilities, and in this case, quite revolutionary possibilities, but does not necessarily provide all the details of how and what. Of course, the way ahead is full of challenges and obstacles which are much more visible to us than the promised land, but I think it is wise to keep an open mind and watch the evolution even if we are not fully engaged or committed or in agreement. Sometimes it is simply better to wait and see than to come to any final conclusions. It is much easier to be dismissive and skeptical of upstart claims of fundamental change than to allow for a slim but real possibility that some new phenomenon could indeed be revolutionary. I wrote previously about CEO shortsightedness and what I called Roryisms. Here is a classic one from IBM that shows h...