My robotic friend? – My (belated) foray into Machine Translation POst Editing (MTPE)

 

As I wrote a few weeks ago, I have made the strategic decision to focus on my competitive advantage – Hebrew to English legal translation. The practical significance of that decision is that I must maximize its potential. Thus, this last week I took on a project involving editing machine translation of an insurance contract. I had previously avoided such projects due to their idiot-savant nature. The project confirmed many of my concerns but, in contrast, demonstrated the advantages of working on machine translation. I discovered that they could indeed be satisfying, both financially and emotionally.

In explanation of the term, machine translation does not necessarily refer to AI engines such as ChatGPT and may include older methods such as Google Translate. The term machine translation designates the initial use of a digital linguistic tool that translates the source text by applying similar patterns in a database, whether vetted and closed or open, Internet-based. Machine translation has existed for several decades, initially through translation memories developed by translators, agencies and companies and expanding to more sophisticated ones based on neural networks. The European Community has developed one of the most specific and sophisticated ones based on previous translations of all EU laws into all of the languages of the community. The open machine translations, notably Google Translate and AI, use statistical probability to choose the most probable translation available on the Internet. The quality of machine translation varies depending on the algorithm, language combinations and sources.

The resulting translation generally resembles one produced by an idiot-savant, which requires neither pure translation nor pure editing. To explain, if a human produces a poor text, it is far more economical in time and energy to retranslate from scratch. Simply put, the editor does not trust anything the original translator did. On the other hand, an editor, identifying an excellent translation, trusts the resulting text in terms of content and merely makes tweaks to improve the language. Furthermore, the editor learns to find a pattern of these mistakes and focus on them. In any case, two pairs of eyes are always better than one, regardless of the skill level. By contrast, machine translation, in my limited experience, produces highly uneven and unpredictable results. One sentence can be perfect, even better than one the editor could write. The next one can be a complete disaster and require complete rewriting. Even more difficult, a given translation may appear correct but closer analysis shows small but significant errors. It requires careful attention to identify those issues. Thus, machine translation is not consistent in quality nor are its mistakes predictable.

In the text I did, the translation engine, DeepL, produced a mixed bag. On the one hand, there were very few content mistakes, i.e., a reader could correctly understand the meaning of the vast majority of the provisions, albeit with a bit of effort and a few terminology errors. On the other hand, it was clear that a human translator had not produced the text. Here is a partial list of the error types:

1.     Articles (he vs. it)

2.    Modals (misuse of “shall” to indicate future instead of legal obligation)

3.    Literal translation of phrases (has the right to instead of may)

4.    Inconsistent capitalization (company and Company)

5.    Translation of the name of the Company

6.    Keeping sentence in the passive (The premium will be paid… vs the Policyholder must pay……

7.    Misplaced adjective (the benefits retained vs the retained benefits)

Thus, the machine translation, while accurate, was not correct.

Upon completion of the project, I decided that I would take on more such projects. Granted, it required great attention, with many breaks, to catch the issues and improve the text. However, the original text was better in some ways than that produced by far too many human translators. Moreover, as I knew that no human was responsible for it, I did not get annoyed. Since I had priced the project by projected time after viewing the translation beforehand (which turned out to be fairly accurate) and offered two different quotes, light and heavy editing, the compensation was more than acceptable. Most importantly, the final text read well, always a satisfying result. Thus, I will now take on more such projects. Maybe robots could be our friends.

Med veg vettings or curious cases of vegetable nomenclatures

 

Mediterranean cuisine is known for its use of vegetables. Curiously, many of the most typical vegetables in the cuisine are not native to the area, meaning they were imported and had to be named. As any player in a telephone game knows, fascinating versions of the original can arise, which can now be seen today in green grocer’s sign in any given country. As an example, the history of the naming of tomatoes, peppers and eggplants shows some of the methods of the madness of naming.

Tomatoes are a staple of Italian and most southern European cooking. They originated in South America. The Aztecs referred to them as tomatl, a name that the Spanish brought back to Europe and is reflected in English and French, among others. However, the Italians received the yellow version of the fruit. As with all exotic foods, marketing is key. Therefore, it was called a  “golden apple”, i.e., pomo d’oro, which became pomodore in one word. The Hebrew story is even more wild. In the late 19^th century when Eliezer Ben Yehuda and others were re-establishing Hebrew as a daily language and inventing words for modern terms, Eliezer Ben Yehuda decided on the word עגבניה [agvania], which is derived from the root for passion or great pleasure. As in most matters in Israel, many people disagreed but eventually agvania became the known and accepted term of this omnipresent vegetable. Marketing and accidents of import had an impact.

Peppers, another South American immigrant to European kitchens, also took a curious path. Europeans had used pepper corns, an imported nut, to spice their food for a long time. With the arrival of peppers, both hot and sweet, the Europeans added an element and confused the matter. Specifically, the word pepper refers both to the plant and spice. See paprika in Hungarian and peperoni in Italian, which also designate the plant. In English, the easy solution was the addition of bell or the color to the vegetable name, e.g., green or bell peppers. However, in Israel, agriculture is a passion. Local agronomists have always sought to improve variants, e.g., the cherry tomato. For example, Israel stores always carry a light green bell papper, ideal for stuffing. It is known as a Nahariya pepper because it was developed near Nahariya, a small town on the coast near the Lebanese border. Israelis are also major consumers of gombot, a red bell pepper. The name derives from an Italian variant, a gamba, and now refers to most large red bell peppers in Israel. Of course, each country has countless variants of this pepper, which is far more than a spice.

Last but not least is the royal eggplant. Probably originally from South Asia, it traveled via Persia, North Africa and Catalonia to reach European kitchens. The word origin is the Sanskrit vātiga-gama, which means “the plant that cures the wind”, and Arabic al-bādhinjān. That last version explains the French “aubergine” (with the Arabic “the”, al, being absorbed as a root). As for the English eggplant , it appears that initially the English in India were rather fond of a white skinned variant, hence the eggplant. As usual, Hebrew presents the most confusing story. Based on a post on the subject, חציל [hatzil] is a new Hebrew word invented in the late 19th century based on a rare Arabic word, حَيْصَل, [haizal]. As usual, many others suggested alternatives. The eggplant does enjoy a wide variety of calling cards.

It is hard to imagine Mediterranean cooking or any other kitchen without these basic vegetables. Yet, they came as immigrants and experienced the same name confusion as many human immigrants have experienced. A rose is a rose is a rose but it may have a local name, which is all the fun. Nomenclature is a product of both intention and accident also in Mediterranean vegetables.

All pictures from Pixabay

Rebranding or nostalgia ain’t what it used to be

 

This last week, linguists celebrated International Translation Day. Many translator organizations and sites marked the occasion, notably Proz.com, which featured two days of lectures and discussions on the state of the profession. Of course, the speakers mentioned AI numerous times, often in the context of how it impacts the profession. Most importantly, the various speakers analyzed the different ways that translators can continue to make a living given an uncertain future that will definitely include AI. One sentence struck a strong chord: whatever you do, do what you love because your passion affects the quality, which is the most important advantage human translators can have over AI. Furthermore, one lecturer noted there will always be a need for expert translators in specialist fields even with improved AI. In that light, I understand that I need to react to the changes in the market in my over 22 years of translation before it is too late. Unfortunately, I do not receive much pleasure when editing or using AI. Thus, I have decided to embrace my experience, drop my other areas of translation and specialize in one field, specifically Hebrew to English legal translation, as it provides the base for my future in all respects.

When I first started translation in 2004, I knew little of my skills or the translation world and chose to cast a wide net. I started my journey by preparing an inventory of my knowledge, specifically four languages, specifically English, Hebrew, French and Russian, and two areas of knowledge, law and finance. Small translation agencies dominated the market at the time. Thus, it seemed logical to create a multilingual brand with several specializations to catch the most fish. I did not know enough to identify any specific target markets and thus created, in effect, a more general brand.

The market had changed radically since then, primarily due to technology and conglomeration. AI and machine translation of all types have eliminated many market niches, including email and personal translation. At the same time, the same technology has created a strong demand for machine translation post editing (MTPE). On an organizational level, large international corporations have gobbled up one small agency after another, creating large volume, low-cost translation venues at the expense of translator rates. At the same time, it should be noted that many well-paying niches not only exist but are thriving, notably legal, medical, marketing and transcreation, which provide ample opportunity for qualified linguists.

As I considered my future (Yom Kippur is an ideal day for doing that), I finally understood that my initial approach, however relevant it was at the time, is no longer effective. I am now choosing to formally embrace the field I enjoy the most, work most efficiently and am most proficient at [Winston Churchill said it was proper to end a sentence with a preposition]. I will solely focus on Hebrew- to-English legal translation, which is mainly what I have been doing for some 10 years now. I have studied legal writing, especially Plain English. Moreover, I am not only quite efficient in translating and editing legal translation but am more proficient at them than many other translators. Thus, as far as anybody can foresee the future, I feel my career has a solid basis.

Giving up the past is never easy. For that reason, people hold on to objects that no longer have any practical value. I still enjoy reading and speaking French. As for Russian, it is quite a useful language in Israel. I may choose to take on a small appropriate task in those languages. However, there is no feeling like doing a task very well especially if it is something that you enjoy. As for the price of rebranding, it requires redoing my marketing approach but better late than never. It may be fun to look back from time to time but success requires forward-looking.