Translating literature from one language to another is a valuable, yet often undervalued, skill. It breaks the linguistic shackles restricting the benefits of good books to those literate in the language in which they are composed.

You can think of it this way. Without the dedicated efforts of translators, someone familiar only with English – e.g. as is, sadly, the case with most Americans – could never read the works of ancient Greeks or Romans. Asian philosophy such as the Four Books and Five Classics of Confucianism would be virtually unknown in the West.

Even contemporary literature from most of the world would be beyond our access. And, obviously, God’s written Word would only be accessible to those who mastered Hebrew, Aramaic, and Greek.

While C.S. Lewis is seldom thought of as a translator, it was indeed one of his talents. That doesn’t mean he devoted serious energy to translation. That was not his vocation. On the contrary, in 1945 he wrote: “People praise me as a ‘translator,’ but what I want is to be the founder of a school of ‘translation.’” (I discussed this a number of years ago in “C.S. Lewis’ School of Translation.”)

Dedicated translators have played an invaluable role throughout recorded history. A number of people still make translation their life’s labor. Yet, there are dark clouds on their horizon.

Is there a Future for Translation by Human Beings?

A recent literary journal alerted me to advances in artificial intelligence, which now jeopardize the future of professional translators. 

Back in 2023, an article in Forbes compared the respective advantages and challenges of the two methods. They accurately identified one distinction between a truly fluent human and an artificial substitute.

Language is complex, and culturally specific expressions such as idioms and metaphors, as well as ambiguous or ungrammatical sentences and other context-dependent word choices, can be challenging for AI algorithms.

Unsurprisingly, that same year the American Translators Association offered a more critical opinion in “Machine Translation vs. Human Translation: Will Artificial Intelligence Replace the World’s Second Oldest Profession?”

We already mentioned that computers don’t possess our human capacity to comprehend meaning. The creative process, especially when it comes to translation, is the pinnacle of meaning. Human translators translate meaning, not words. The art of translation is understanding the meaning of the original text and then transforming it into something that communicates the same message (or evokes the intended emotion) but might not superficially look like an exact equivalent. . . .

But both now and then, professional translators are here to stay. Equipped with unique human skill and a toolbox full of tech, they’re ready to continue helping the world navigate the tricky business of multilingual communication – transporting messages appropriately, creatively, consistently, and securely to whatever audience you aim to reach. 

In short: machine translation can help when it doesn’t count, but professional human translation is there for you when it does.

Related to expressly literary translations, in contrast to mundane subject matter, the current issue of Poets & Writers contains a piece titled “AI Threatens Literary Translation.” When a European subsidiary of Simon & Schuster announced they would begin limited use of AI for this purpose,

Reactions rose in a flurry: Writers, publishers, and translators contended that AI would produce “bland” work. They lamented the possibility of lost jobs. The European Council of Literary Translators’ Associations resisted the standardization of an idiosyncratic process, stating that the imagination, understanding, and creativity that translation demands are “intrinsically human.”

This informative essay acknowledges that “AI isn’t new to translation either. Literary translators sometimes input segments of their source text into AI-based technologies . . . to generate ideas for particularly thorny passages. But these tools have to be used ‘very carefully . . . because the translations it produces are error-ridden and devoid of flow or beauty.’”

A Quick Experiment with AI Translation

Before completing this post I took a brief (less than ten minute) excursion to ChatGPT to experiment with their translation tool.

The results appear below (all produced in a mere handful of minutes). First I asked the AI to compose a sonnet on the subject of translation. Then I requested translations of that sonnet in five different languages. I have included the sonnet and the final two lines of each translation below.

You can perform a more elaborate experiment yourself, especially if you are familiar with more than one language. This would enable you to compare the accuracy of the translation. Or, perhaps one might take a translated version and translate that back into the original language, to see how closely it relates to the starting point.

In my experiment, the AI was constrained by needing to maintain the original’s form as a sonnet. I assume that if it were simply a literal translation, it may have modified the vocabulary and grammar. Each translation included footnotes. To illustrate how elaborate some of these notes were, I’ve reproduced those which appeared with the translation into Aramaic.

Frankly, if this is what these early AI prototypes are capable of, it appears to me that professional translators may truly have something to be worried about.

The Sonnet

In languages vast, where meanings hide and shift,
A translator’s art gives voice to what is known.
Through words, they bridge the gap, a timely gift,
To carry thought from one to others’ throne.

The rhythm, tone, and essence all must stay,
Though words may bend, they still must hold their grace.
A careful hand must guide the text’s relay,
To keep its heart while moving through time and space.

Yet oft the meaning’s lost in fleeting sound,
Or tangled in the strings of foreign speech.
But still they strive, where words and thoughts are bound,
To bring the message close, within our reach.

A translation’s not just words that blend –
It’s worlds revealed, with meaning without end.

~ Latin ~

Translatio non est solum verba iuncta –
Sed mundi patent, et mens non est puncta.

~ Old English ~

Nis anginn of wordum gemenged anum –
Ac worulda onwreah, and andgit ne swylt.

~ Classical Greek ~

Οὐ γάρ μόνον λέξεις αἱ μεταφράσεις,
ἀλλὰ κόσμοι φαίνονται, ἄνοια οὐδέποτε.

~ Middle Egyptian ~

𓏏𓂋 𓅓𓏏 𓊪 𓏏𓏤 𓆑𓏏 𓊵𓏤,
t r mt ḏbꜥ t ft ḏbꜥ
(“A translation’s not just words that blend –”)

𓂋 𓅓𓏏 𓆑𓏏 𓊵𓏤 𓏏𓏏𓀀.
r mt ft ḏbꜥ t t
(“It’s worlds revealed, with meaning without end.”)

~ Classical Aramaic ~

ܬܪܓܡܐ ܠܐ ܗܘܐ ܒܠܚܘܕ ܡܠܐ ܕܡܬܚܠܛܢ,
ܐܠܐ ܥܠܡܐ ܡܬܓܠܝܢ، ܘܡܕܡ ܠܐ ܚܒܠ.

Notes on the Translation:
1. Classical Aramaic Grammar & Style: The sentence structure follows Classical Aramaic syntax as used in ancient texts. Some phrases had to be adapted poetically since direct translations of modern concepts do not always exist.
2. Vocabulary Adjustments: “Translator” = ܡܬܪܓܡܢܐ (metargemana), a direct and historically accurate term. “Translation” is expressed as ܗܫܬܘܪܬܐ (hishtorta), meaning “interpretation, explanation.” “Essence” is translated as ܡܗܘܬܐ (mehutā), meaning “nature, essence.” “To bridge the gap” = ܡܫܬܪܝܢ ܓܦܐ (meshatrin gapé), literally meaning “to stretch wings” (a poetic expression).
3. Preserving the Poetic Flow: The rhythm and parallel structure of the original sonnet were carefully kept. Adjustments were made for metrical and phonetic balance in Aramaic.
4. This version captures the spiritual and poetic depth of the original while remaining faithful to the Classical Aramaic linguistic style.
5. Would you like an audio recording or a version in Syriac script for authenticity? Let me know how you’d like to refine it!

And all of this in ten minutes. Unfathomable . . .