Natural Language Processing or (NLP) can best be described as the field of computer science, artificial intelligence, and linguistics concerned with the interactions between computers and human languages. NLP ties into translation through use of Machine Translation (MT), which is known as the task of automatically, converting one natural language into another, preserving the meaning of the input text, and producing fluent text in the output language. Other types of NLP include information extraction, sentiment analysis and question answering.
NLP was â€œdiscoveredâ€ in the 1950s by Alan Turing, whoâ€™s â€œTuring Testâ€ (test of a machine’s ability to exhibit intelligent behavior equal to, or indistinguishable from, that of a human) is one the determinants of intelligence.Â Later, in 1954, the Georgetown experiment (involving the fully automated translation of more than 60 Russian sentences into English) was conducted with the hope that within five years, machine translation would be a solved problem.
In 1964, a committee of seven scientists, the Automatic Language Processing Advisory Committee, was established by the US government for the purpose of evaluating the progress in machine translation. The findings of this committee, known as the ALPAC report was issued in 1966, gained notoriety for being very skeptical of research done in machine translation so far, and emphasized the need for future research and eventually caused the U. S. Government to reduce its funding of the topic dramatically.
Later in the 1960s, many other advances in NLP were made, most notably, the ELIZA computer program (based on Carl Rogers and his client-centered brand of talk therapy) which was an early example of primitive NLP. Â ELIZA operated by processing users’ responses to scripts, the most famous of which was DOCTOR, a simulation of a Rogerian psychotherapist. Â Using almost no information about human thought or emotion, DOCTOR sometimes provided a startlingly human-like interaction.
Throughout the 1970s and 80s, new trends in NLP started to emerge. Many programmers began to write â€œconceptual ontologiesâ€ in the 1970s which structured real-world information into computer-understandable data and chatterbots (computer programs designed to simulate an intelligent conversation with one or more human users via auditory or textual methods, primarily for engaging in â€œsmall talkâ€) were also employed. Up to the 1980s, most NLP systems were based on complex sets of handwritten rules. During the late 1980s, however, we started to see the development of the cache language models upon which many speech recognition systems now rely.Â While Google has made great strides with NLP and MT, the challenge is still maintaining the integrity of sentence structure.
Moving forward, try to imagine talking to your computer and having it talk back to you in a fluid style.Â Appleâ€™s Siri is a great example of where NLP is headed but it is only the tip of the iceberg. According to my research, as NLP technology advances computers will have a much easier time understanding us.
Filed under: Language, Language Learning, Multiculturalism, Software Localization, Translation Services, Web Localization
We have all seen many instances of literal translations of slogans into foreign languages that just donâ€™t work. Thankfully, transcreation can take care of this issue.Â Transcreation (also referred to as â€œcreative translationâ€) has been a hot topic in recent years, especially in the global market sector. It has been described as both the process of adapting precise brand content from one language into another and the transformation of an overall message which addresses written content, visual design and imagery. Standard translation and localization services don’t effectively preserve the creative and emotional intent of the content that allows it to best resonate in other languages and cultures.
Although it is a term mainly used by advertising and marketing professionals to refer to the process of adapting a message from one language to another, many localization vendors are now offering it as one of their client services. Â In other words, translation is to transcreation what writing is to copyediting.Â Simply put, it is a way of conveying the same message put forth by the source text to target audiences in language that the target audiences readily understand.
However, transcreation can be a difficult process. Working on the client-side of localization many years ago, we marketed to a younger audience and words like â€œphatâ€ were used.Â I remember thinking how are we going to convey what â€œphatâ€ (depending on the source, it means â€œexcellentâ€, or â€œvery coolâ€ or to others, it is an acronym for â€œpretty hot and temptingâ€) means in Sweden.Â This is part of the process of transcreation; in this case, finding the equivalent of what â€œphatâ€ conveys in English in Swedish. Simply using the word â€œphatâ€ (unless commonly used in English) will just not work and the proper message will not be conveyed.
The well-known slogan for McDonaldâ€™s is â€œIâ€™m loving itâ€.Â This works fine for America where we â€œloveâ€ our shoes, our pets, our husbands, our girlfriends, our favorite movie, etc. The same word is used for the love for all of those things. However, in Chinese, the word â€œloveâ€ is used only for deep, meaningful love so the slogan in Chinese translates as â€œI just like itâ€.
Another difficulty faced is that many client logos contain puns and since logos are not to be translated, these puns are not easily understood by the end users.Â Clients should keep this in mind (if going global) when creating their logos.
Spiderman India is a well-known example of transcreation and the first of its kind where a Western property is rewritten and rebranded.Â The name Peter Parker was changed to the more ethic-sounding Pavitr Prabhakar and instead of chasing the Green Goblin, he chases a demon known as Rahshasa.
To find out more about transcreation and whether your product requires it, please contact ABLE Innovations today to speak to one of our seasoned professionals.