Just a few years ago, you could often tell when a text had been machine-translated by how hard readers were laughing. Sentences like \u201cThis device will not tread in rust before the end of five years\u201d left little doubt as to whether they had been produced by a person or a computer. <\/p>\n\n\n\n
Today, however, you won\u2019t find many laughing about machine translation (MT). Indeed, the past several years have seen it evolve from a primitive solution for emergencies into an alternative that has to be taken seriously in the translation market. This hardly means that human translators<\/a> should start looking for new jobs, though \u2013 or that you\u2019ll be able to leave your own translations to Google or DeepL in the future. <\/p>\n\n\n\n In this article, you\u2019ll learn about the kinds of texts that are suitable for machine translation and which should be entrusted to a living, breathing expert. To find out which method will best meet your needs, simply read on. <\/p>\n\n\n\n Thanks to huge strides in artificial intelligence and computational linguistics, the performance of machine (or automatic) translation solutions has advanced significantly in recent years. In early 2018, specialists from Microsoft Research<\/a> caused something of a stir when they claimed to have achieved parity in Chinese-to-English machine translation \u2013 meaning that their results were indistinguishable from those produced by a human. <\/p>\n\n\n\n While the team\u2019s bold statements should be taken with a grain of salt<\/a>, there\u2019s no question that the quality delivered by machines is fulfilling ever higher expectations. This is mainly due to the fact that modern translation programs are capable of processing tremendous amounts of data (i.e. text) in just seconds. As a result, their output now bears little resemblance to the meaningless hodge-podge of words typically churned out by translation software a mere decade ago. In some cases, they actually do come impressively close to the work of a human translator. <\/p>\n\n\n\n The quality of the text produced fundamentally depends on the type of machine translation applied. Here, we differentiate among three different approaches: rule-based, statistical, and neural MT. <\/p>\n\n\n\n This method analyzes the source text and restructures it in the target language based on linguistic and grammatical rules, as well as dictionary templates. While its results are consistent, they can range from useful to somewhat silly depending on the text and language pair at hand. <\/p>\n\n\n\n Statistical systems \u201clearn\u201d how to translate by analyzing massive sets of data. The translation itself is then performed based on bilingual text corpora that provide statistical probability models. The results have a certain flow, but are less logical. <\/p>\n\n\n\n Neural machine translation<\/a> (NMT)\u202frelies on complex neural networks. In this approach, associations are produced for each individual word based on those adjacent to it. The more training material a system receives, the more accurate its translations become. <\/p>\n\n\n\n While NMT is still relatively new, it\u2019s becoming increasingly popular. And it\u2019s not just private users and frugal companies that are taking advantage: More and more professional translators are using the natural-sounding output NMT can quickly provide as a way to increase their own productivity. <\/p>\n\n\n\n Automatic translation can be worth a look in certain situations. If you want to translate texts for internal use, for example, and the information itself is more important than how well it\u2019s presented, a machine translation tool might be just what you\u2019re after. <\/p>\n\n\n\n Here are some possible candidates for MT: <\/p>\n\n\n\n These example applications all require prior deep-learning<\/a> training of the MT solution used in order to produce accurate results in the context at hand. <\/p>\n\n\n\n Just because someone speaks a language doesn\u2019t mean he or she is good at writing it. The same applies to computers. By the same token, not everyone has a knack for blogging, writing copy, or crafting bestsellers. This is why texts that need to meet a certain standard of style \u2013 to evoke emotion or win the reader over, for instance \u2013 aren\u2019t a good fit for a machine. Technical content featuring complex sentence structures and specialist jargon also requires a human touch. <\/p>\n\n\n\n Take a phrase like \u201ctighten our belts\u201d: While AI is getting better and better at making sound assumptions based on context, a translation program won\u2019t always know whether a company\u2019s revenues are down or waistlines are actually involved. Problems can also arise when key terms need to be translated differently within the same document. The German word Anfrage, for example, can mean \u201crequest\u201d, \u201cinquiry\u201d, or \u201cquery\u201d in English. An MT solution without the capacity for memory might not be able to determine which translation is appropriate in each case. <\/p>\n\n\n\n Meanwhile, there\u2019s something else machine translation lacks: cultural insight. Particularly in the field of marketing, it\u2019s important to account for the local idiosyncrasies of your target market. Imagine a U.S. manufacturer of spider spray wanted to advertise its product\u2019s effectiveness against black widows and brown recluses in Europe. It could save itself the trouble of translating this message into one language, at least: These species aren\u2019t common in Germany! An experienced translator would bring this to the company\u2019s attention and perhaps suggest some poisonous pests that are actually prevalent in the country. <\/p>\n\n\n\n So far, we may have given you the impression that machine translation has no business handling content meant for PR purposes, but that isn\u2019t exactly true. With relatively little effort, the raw translations produced with such solutions can be refined into texts that hold up to public scrutiny. This type of post-editing is an interesting option for companies because it sometimes enables them to avoid considerable costs. <\/p>\n\n\n\n Human translation can get expensive, after all \u2013 especially when large amounts of text are involved. This is where post-editors come in: These qualified translation specialists have in-depth knowledge of a particular language pair, which enables them to polish machine-translated texts to a shine. At Lexsys, our post-editing experts will leverage their extensive experience in translation, proofreading, and revision to ensure that your machine-translated texts read like they were written by a professional native speaker. <\/p>\n\n\n\n Whether you\u2019re already making active use of MT or are still weighing up the pros and cons, we can help you transform your texts into appealing translations without stretching your budget. If you\u2019d like to learn more about how we can meet your needs,\u00a0contact us<\/a>\u00a0today to set up an appointment.<\/p>\n","protected":false},"excerpt":{"rendered":" Machine translation (MT) is becoming increasingly powerful. Provided that it is followed by proper post-editing, MT can certainly result in high-quality texts. But there are limits. Find out more!<\/p>\n","protected":false},"author":3,"featured_media":1886,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[30],"tags":[35],"class_list":["post-1804","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-translation-en","tag-machine-translation"],"_links":{"self":[{"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/posts\/1804","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/comments?post=1804"}],"version-history":[{"count":1,"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/posts\/1804\/revisions"}],"predecessor-version":[{"id":1889,"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/posts\/1804\/revisions\/1889"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/media\/1886"}],"wp:attachment":[{"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/media?parent=1804"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/categories?post=1804"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lexsys.de\/en\/wp-json\/wp\/v2\/tags?post=1804"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}Machine translation continues to improve <\/h2>\n\n\n\n
Rule-based machine translation<\/h3>\n\n\n\n
Statistical machine translation <\/h3>\n\n\n\n
Neural machine translation <\/h3>\n\n\n\n
When does machine translation make sense? <\/h2>\n\n\n\n
\n
What are the limits of machine translation? <\/h2>\n\n\n\n
Post-editing to ensure quality <\/h2>\n\n\n\n