just put everything in Deepl, and then read both the original and the translation, side by side, and fix the mistakes
Well, actually this is also my typical workflow with Google Translate (I was aware of the existence of Deepl, I just mentioned Google Translate because it’s more widely known). Maybe it got better in the last two years?
try to translate an Italian opera written 100 or 200 years ago, Google Translate just writes random words, Deepl gets it right.
I just tried with the most obscure scene I know of (Scena 13 from The Night Bell), which was deliberately written to be full of near-incomprehensible words even for its time. The results from Deepl and Google Translate seem pretty similar to me; in several cases Deepl is the one who gets it wrong (even at the very start: “mi dovete una ricetta come un fulmine spicciar” is correctly translated as “you owe me a recipe like a flash of lightning” by Google Translate, while Deepl writes “you owe me a recipe like lightning spicciar”).
Anyway, this was precisely my point: these systems can significantly speed up the work of human translators, but not completely replace them (yet), because some form of proofreading is still needed, and for now the only way to proofread the translation is to have a human who knows both languages.
Eccomi in lieta vesta... Eccomi adorna... come vittima all’ara Oh! almen potessi qual vittima cader dell’ara al piede! O nuziali tede, aborrite cosi, cosi fatali, siate, ah! siate per me faci ferali. Ardo… una vampa, un foco tutta mi strugge.
Un refrigerio ai venti io chiedo invano Ove sei tu, Romeo? in qual terra t’aggiri? Dove, dove, inviarti, dove i miei sospiri?
Google Translate:
Here I am in happy dress... Here I am adorned... as a victim in the arena Oh! at least I could as a victim fall of the altar at the foot! O German nuptials, abhor you so, so fatal, be, ah! be for me feral faci. I burn… a blaze, a fire everything torments me.
A refreshment to the winds I ask in vain Where are you, Romeo? in which land are you wandering? Where, where, to send you, where my sighs?
Deepl:
Here I am in happy attire... Here I am adorned... As a victim at the altar Oh! at least I could what victim Fall of the altar at the foot! O nuptial tede, abhorred So, so fatal, Be, ah! be for me Faci ferali. I burn, a blaze, a fire All cringes at me.
A refreshment To the winds I ask in vain Where art thou, Romeo? In what land wanderest thou? Where, where, send thee, where my sighs?
A human translator:
Here I am in a happy attire Here I am adorned… like a victim for the altar. Oh, if I could at least fall a as a victim at the foot of the altar! O nuptial torches, abhorred, so fatal, ah, be my funeral torches. I am burning… a flame, a fire consumes me entirely.
In vain I beg the winds to refresh me. Where are you, Romeo? In what parts are you roaming? Where, oh, where can I send my sighs to you?
Let’s compare...
“vittima all’ara”—GT “a victim in the arena” wrong; D “a victim for the altar” correct
“almen potessi qual vittima cader dell’ara al piede”—GT “at least I could as a victim fall of the altar at the foot” correct; D “at least I could what victim fall of the altar at the foot” almost ok
(this is the part where GT now does significantly better than one year ago, when it translated “ara” as a parrot, so the victim was falling at parrot’s feet. D already understood that it was an altar.)
“nuziali tede”—GT “German nuptials” wrong; D “nuptial tede” wrong
“faci ferali”—GT “feral faci” at least it partially tried, but got it wrong anyway; D “faci ferali” just gave up
“un foco tutta mi strugge”—GT “a fire everything torments me” almost ok; D “a fire all cringes at me” wrong
Well, actually this is also my typical workflow with Google Translate (I was aware of the existence of Deepl, I just mentioned Google Translate because it’s more widely known). Maybe it got better in the last two years?
I just tried with the most obscure scene I know of (Scena 13 from The Night Bell), which was deliberately written to be full of near-incomprehensible words even for its time. The results from Deepl and Google Translate seem pretty similar to me; in several cases Deepl is the one who gets it wrong (even at the very start: “mi dovete una ricetta come un fulmine spicciar” is correctly translated as “you owe me a recipe like a flash of lightning” by Google Translate, while Deepl writes “you owe me a recipe like lightning spicciar”).
Anyway, this was precisely my point: these systems can significantly speed up the work of human translators, but not completely replace them (yet), because some form of proofreading is still needed, and for now the only way to proofread the translation is to have a human who knows both languages.
My example was a version of Romeo and Juliet:
Google Translate:
Deepl:
A human translator:
Let’s compare...
“vittima all’ara”—GT “a victim in the arena” wrong; D “a victim for the altar” correct
“almen potessi qual vittima cader dell’ara al piede”—GT “at least I could as a victim fall of the altar at the foot” correct; D “at least I could what victim fall of the altar at the foot” almost ok
(this is the part where GT now does significantly better than one year ago, when it translated “ara” as a parrot, so the victim was falling at parrot’s feet. D already understood that it was an altar.)
“nuziali tede”—GT “German nuptials” wrong; D “nuptial tede” wrong
“faci ferali”—GT “feral faci” at least it partially tried, but got it wrong anyway; D “faci ferali” just gave up
“un foco tutta mi strugge”—GT “a fire everything torments me” almost ok; D “a fire all cringes at me” wrong
...well, now GT is narrowly a winner.