How could real-time sentence translation work if using a "common middle ground" language?

Question

Previously I'd developed a concept for a translation process that uses a common language, but is perceived (using technology or some other sort of device/substance that can alter mental processing) to each user as their own native language. To put it simply: speaker thinks in their native language >>> speaker says the sentence in the Common Language, but to them it sounds and feels like their native language >>> listener perceives the spoken Common Language sentence and subconsciously understands its meaning >>> the understood sentence is perceived consciously as the listener's native language.

But one big question I encountered as I considered this idea was: how could this process work across different languages' word orders? The Common Language actually being spoken may have a flexible word order for easy real-time speaking and usage regardless of a user's native grammar; but is there a way that, for example, a native subject-verb-object listener would be able to perceive a sentence-object-verb sentence's "translation" to their own language in (more or less) real time, especially if they technically are still understanding the actual meaning via the shared Common Language first? For example could there be some function or element of the Common Language itself, or of the device/substance's ability to alter the process of language comprehension/perception, that could help account for this?

Answer 1

You're overthinking it. This happens all the time with bilingual speakers. Their native tongue may order words in one way, but their learned language orders words a different way. When such a person hears a sentence in that second language, they hear the words in whatever order, and then their conscious mind rapidly interprets to create the appropriate meaning.

When two people speak, they are not conveying individual words, they are conveying concepts and meanings. Even when two people with the same native tongue speak together, conveying a complete sentence or thought takes time. Their brain is rapidly analyzing and conveying meaning while the sentence is being spoken, until the thought is complete. Sometimes the meaning is achieved even before the entire sentence is spoken, for example when idioms are used. If I were to say, "Out of the frying pan, into the fire." then most native speakers can understand my meaning by the time I finish saying "pan," or even earlier depending on context. So much so that it would be entirely natural just to say, "Out of the frying pan..." and trail off to silence, and everyone would still get my meaning.

If you are envisioning an actual mechanical device in someone's ear, this is not a problem. The device simply transliterates each word individually, and then it's up to the listener's subconscious/conscious brain to assemble the whole meaning. Again, this is exactly what bilingual speakers do all the time, and it would be virtually unnoticeable by the users after a short period of adjustment.

Answer 2

Fun idea.

The use of the common language is a red herring. In the end, a sentence formulated in the speaker's language has to be cast in the listener's language.

^{In the field of automated translation, this approach is called interlingual machine translation. The text in the source language to be translated is transformed into an interlingua, that is, either a pivot natural language or an abstract language-independent representation, and the text in the target language is then generated from the interlingua. Nowadays, this approach is used when automatically translating between languages for which the direct translation path is much less well developed than translation paths to and from a pivot language, quite often English.}

Let's try Latin to English: the speaker formulates the sentence "hi omnes linguâ, institutis, legibus inter se differunt". The listener must hear "all these differ from each other in language, institutions, and laws".

Latin	English (word-by-word)
Hi omnes	These all
linguâ,	in language
institutis,	in institutions,
legibus	in laws
inter se	between them
differunt.	are different.

The translator begins all these, but then must pause and wait until the lips or the mind of the speaker reach differunt because English absolutely wants a verb after the subject, and Latin (in normal prose) is very reluctant to put it there. The translation simply cannot continue until the Latin sentence reaches its verb, because the translator cannot look into the future, and the speaker may have wanted to say similes sunt (are similar)...

In practice, speakers who deliver a speech with simultaneous translation into one or more other languages, are instructed to keep their sentences as short as practicable and to pause after each sentence to allow the translators to translate. (In better venues, where simultaneous translation is often performed, the speaker's lectern may even feature a red and a green light, controlled by translators; the speaker speaks when the green light is on, and pauses when the red light is on.)

Or else, maybe the culture has evolved to be tolerant of Master Yoda-speak: after all, rendering
"interea eâ legione quam sécum habebat militibúsque, qui ex provinciâ convenerant, à lacu Lemanno, qui in flumen Rhodanum influit, ad montem Juram, qui fines Sequanorum ab Helvetiis dividit, milia passuum XVIIII murum in altitudinem pedum sedecim fossámque perducit"
as
"in the meantime, with the legion he had with him and with the soldiers who from the province had come, from lake Leman, which in the river Rhone flows, to mount Jura, which the borders of the Sequans from the Helvetians divides, a 19 miles wall, in height sixteen feet, and a ditch, he carries" is sort-of intelligible, even if bad English.

(Of course, the correct translation would be
"in the meantime, with the legion he had with him and with the soldiers who had gathered from the area, he builds a wall 19 miles long and sixteen feet tall, and a ditch, from lake Leman, which flows in the river Rhone, to mount Jura, which separates the lands of the Sequans from the Helvetians".)

(Olde skoole English translations have "in the meantime ... he carries a wall" etc., but in contemporary English "he builds" is much better, as that particular usage of "to carry" is no longer in use.)

(For some strange reason, Lake Leman is most often called Lake Geneva in English, or so Wikipedia informs me. Dear native English speakers, that lake has a proper name, which has been in use for thousands of years.)

^{The examples are taken from Caesar's Commentaries on the War with the Gauls, which is written is a very straightforward and clear style, quite often being the first for-real Latin text assigned to beginners to parse and translate.}

---

To preserve real-time communication a very much better idea is to have both the speaker and the listener actually learn the common language, possibly materialized in different phonetic or signalling forms. A person who actually knows a foreign language to any level better than first year beginner is perfectly able to think in the foreign language, and to follow a sentence in real time, without having to wait for all the pieces to come in so that they could cast it in their native language. The automatic mind-to-mind translator would still have to supply the meanings of common language words which the speaker or listener doesn't yet know, but that is comparatively much easier.

Answer 3

Time to invoke some Clarkean Magic

I know two languages: my native English and Finnish. English tends to put the subject before the verb. Finnish tends to put the subject after the verb. (thanks @JaniMiettinen for refreshing an old memory.) English prepositions are individual words. Finnish prepositions are suffixes. English can make some pretty complicated sentences...

But Finnish can make some enormously complex words...

...because Finnish has endings that convert verbs to nouns and nouns to verbs and produce scope and establish ownership and operation and a zillion other things. Frankly, Finnish can express in one word with character count X what would take English a lot of words with character count Y and X<<Y.

I'll be honest with you, without Clarkean Magic, the idea of translation from one language to an intermedite language to a third language in real time is unrealistic. It's one of the reasons why most authors either don't deal with the details or invent the proverbial babel fish. I'm going to underscore the problem with the idea of alien, truly alien, life. While human language covers a massive range of sounds and actions — we all have access to those same sounds and actions.

An alien mouth, larynx, lungs... and more... may be very, very different...

What's the point?

There comes a time in every worldbuilder's experience when one must decide whether or not the detail makes any sense. In this case, I don't think it does. It would be (and is... and will be...) difficult if not impossible to create an accurate translation without waiting until the end of at least a sentence — and frequently more. You should take some time reviewing questions over at English.se and English Language Learners.se. It's frequently impossible to understand the the question without havaing more than one sentence because context is needed to translate the sentence.

Example: "I'm sorry" has two translations in Finnish:

• "Mina olen Pahoillani"
• "Aanteksi"

Without knowing the context, the English phrase can't be accurately translated into Finnish. Frankly, without context it would be hard to translate either of those Finnish phrases into English.

But let's invoke some clarkean magic

1. To a degree, your "system" can look ahead and predict what the probabilities are of what will be said next.

2. It can do that with reasonable accuracy because it's looking behind and keeping track of the conversation, so it understands the context behind what's being said.

3. And it does all this for every language known at such a high speed that if it happens to detect an error in translation, the correction is taken in stride as we do when we mishear or misunderstand someone.

In other words, with a bit of Clarkean Magic, you have a solution that wouldn't be disimilar to pretty much any conversation humans have with one another right now.

But to try and work out the details of how this happens? IMO, that's a waste of time as any solution you come up with will likely be inadequate even for human languages, much less alien languages.

Answer 4

No Problem

The brain already has some leeway in terms of time. When you read text you do not read one word at a time. You read three of four words at a time. When you listen to a person speak, you do not hear the words one at a time. You also remember the previous word while predicting the next one.

The translation does not translate one word at a time. The creators were aware that a single word cannot be translated in isolation without its context to give meaning. In English, suppose the first word of the sentence is "Dry." The translation into Alieneese will be different depending on if the second word is "desert" or "wine". The meanings are different. The first means lacking moisture and the second means lacking sweetness. Alieneese does not have the coincidence where the two meanings have the same word.

No, the translator traslates one semantic chunk at a time. The chunks themselves are independent of word order. Sometimes they arrive a bit muddled. But users quickly become accustomed to this muddling, and don't notice it any more than you notice your fingers moving over the keyboard as you type.

Answer 5

True real time translation is practically impossible in general use

Many answers have already brought up problems, but possibility of garden path sentences is the nail in the coffin. From Wikipedia:

A garden-path sentence is a grammatically correct sentence that starts in such a way that a reader's most likely interpretation will be incorrect; the reader is lured into a parse that turns out to be a dead end or yields a clearly unintended meaning. "Garden path" refers to the saying "to be led down [or up] the garden path", meaning to be deceived, tricked, or seduced.

The text refers to reader, but listener will be tricked just the same way. If you try to translate such sentence real-time, you have high probability of starting the sentence completely wrong way, and you need to redo it once the sentence has been finished.

An example from Wikipedia will clarify the problem: The complex houses married and single soldiers and their families.

You probably had to reread it to make any sense of it.

Answer 6

How do people translate?

I was taught French at school, with all the rules for singulars and plurals, irregular verbs, and all that jazz. People who translate (my sister is good at this, and my father was the same) will mostly do this subconsciously. Translation is not done with a set of rules. There are no good dictionaries that will give you an exactly equivalent word. However, if you can speak in a language, then relax and just do it. I have never had the knack, but people in my family can.

We have recently understood that AI models can imitate a lot of what people do. We don't have to imitate the process of learning grammar: we can just scrape the statistics from a large enough database, and it seems to work. I suspect the 'common middle ground' language is the sort of thing that Esperanto, Interlingua, or Volapuk were trying to do, but this is not the way we would do it today.

Answer 7

Honestly I found your scenario eyebrow raising as it implies an awful lot of some implant hijacking the speakers vocal chords for an unnecessary translation middle man.

But something analogous might be the Star Trek TNG episode 11001001.

The Binar species has a implant that lets them communicate with each other in modem chirps. The episode claims their brains even think in this high speed language. However they can speak English. Though possibly this might be some other alien vocal language converted to English by the universal translators. Note in star trek the universal translator is like tv and film- just because you hear foreigners speaking English with each other doesn't mean they are - it's just to spare the audience from subtitles. (In hindsight in-universe there's no reason the universal translator couldn't have translated the modem chirps too.)