Cool. There is actually a W3C draft spec for Mongolian script![1]
We tend to assume that left-to-right script is a law of nature but it is just one of many variations that have been invented and used across space and time. Right-to-left (Arab / Hebrew) [2] is well known but a most intriguing one used in antiquity by Greeks and others is Boustrophedon (alternating from left-to-right / right-to-left).[3]
Boustrophedon mode is in one sense the optimal script form. At the one-time expense of having to learn to recognize letters and words both ways one can then (in principle) speed up reading as the eyeballs don't need to jump across the page to start a new line :-)
It was the attempt to translate Egyptian hieroglyphs into Phoenician which led to all of today's alphabetic languages. Archaeologists recently found a temple in the Jordan area in which the earliest known attempt at an alphabetic language was written; it was a translation between Egyptian and Phoenician.
Alphabetic, non pictographic languages are an order of magnitude easier to learn and express than pictographic languages, which require rote memorization of hundreds to thousands of pictographs and their modifiers. In contrast, the language you're reading this post in allows you to guess the sound of the words by the spelling, which is simply impossible in, say, Mandarin.
I agree with your point in general, that alphabetic systems are easier to pick up. However, it’s not true that you can’t guess the sound of a Chinese character. From Wikipedia [0]:
Radical–phonetic compounds, in which one component (the radical) indicates the general meaning of the character, and the other (the phonetic) hints at the pronunciation. An example is 樑 (liáng), where the phonetic 梁 liáng indicates the pronunciation of the character and the radical 木 ('wood') indicates its meaning of 'supporting beam'. Characters of this type constitute around 90% of Chinese logograms.
Note that the "phonetic" component can become incredibly strained in modern Chinese languages. Eg, take the character "俞"; in Mandarin, it's pronounced "yú". However, it's used as a phonetic component in:
1) 输: pronounced "shū"
2) 偷: pronounced "tōu"
(There are even worse examples which I can't think of in the moment)
That brongs up the question? Are there actually alphabet based languages which are worse than English at pronunciation - transcription correspondence? The few I know are all better.
I loved learning to read Japanese through the second volume of Heisig's _Learning the Kanji_. Volume 1, which teaches only meanings, is a slog, but volume 2, which teaches the Sino-Japanese readings is a beautiful example of organizing material to minimize entropy and maximize benefit for memorization as soon as possible. Unfortunately he never put together a volume 2 for a Chinese language. I haven't worked on it in a while, but I have a project where I attempt re-create the book for Japanese as well as Mandarin, Korean, and Vietnamese: https://nateglenn.com/uniunihan-db/ (repo: https://github.com/garfieldnate/uniunihan-db).
The "pure groups" are the ones where the presence of a specific radical guarantee you a specific pronunciation (within the list of character/pronunciation pairs you're trying to learn). Of the 4800 characters I used for the volume, only 290 are in the chapter on pure groups. The rest are either in semi-regular groups with varying numbers of exceptions, or in completely irregular groups with no discernible patterns.
The characters were designed continuously over a period of time starting thousands of years ago, and the phonetic parts were sometimes exact and sometimes just clues, similar sounds or rhymes to give the reader a hint. Ancient Chinese pronunciation has changed beyond recognition, so it makes perfect sense that the pronunciations wouldn't be regular anymore.
Mainland China uses a "simplified" character set, which did not affect literacy but in my opinion is a bit more difficult to read; they reduced the number of lines so that more characters look samey and they combined many (Mandarin) homonyms (https://en.wikipedia.org/wiki/Simplified_Chinese_characters#...), removing the meaning portion of characters that would have distinguished them. The simplification did not apply to all characters, so to achieve a high level of literacy you need to know traditional forms, anyway.
It would be interesting to see someone try to actually remodel hanzi from scratch for a specific dialect of Chinese, using 100% regular phonetic components and no variants; multiple pronunciations of a character in the current system would be required to be written differently. An interesting example of this would be certain Korean gukja, where they've combined a Chinese character with a phonetic hangeul (example: https://en.wiktionary.org/wiki/%E3%AB%87). This would be a truly simplified Chinese character set... but all of the culture's history that gets built into spelling over time would be completely lost, which is why I always prefer conservative spelling systems.
> the language you're reading this post in allows you to guess the sound of the words by the spelling
It is "a guess" at best, and that guess won't be correct most of the time, unless you know the word already. And when you don't, you'll be dealing with all kinds of Cansas/Arcansas and although/drought/through/bought/cough/enough most of the time.
In e.g. Russian or German, you can read the word from the way it is written and maybe miss the accent. In e.g. Spanish you can read the word correctly with the right accent most of the time. Even Korean is more phonetic than English - in English the best you've got is a guess.
Not unlike Mandarin, by the way.
Source: non-native speaker of English, also speaker of some other languages.
The spelling of English words gives you two separate clues:
1. How it is pronounced.
2. Its etymology and what it means.
Because pronunciation has changed over time and changes across regions, these two features are in conflict. If we made spelling uniformly reflect (current, in some given place) pronunciation, then we would lose clues as to etymology and meaning.
For example, an English speaker can reasonably guess that "native", "nation" have related meanings because of the shared "nat". If we made the spelling follow pronunciation and did "naytiv" and "nayshun", some of that is lost.
Ideally, pronunciation would be fixed across time and place so that a language's spelling reliably reflected both meaning and sound. But that ain't how humans work.
In written languages that do this "better", it's mainly through some combination of:
1. The written language is simply younger than written English and thus has had less time for pronunciation to diverge.
2. The language is used by a smaller, more homogeneous community.
3. Elites exert political force to prevent pronunciation or meaning from changing and to reject loanwords at the loss of expressivity.
English does none of those things. It's been around a long time, has spread throughout the world across widely disparate communities, and is happy to absorb any good idea it finds in any other language. It is the Perl of written languages, for better or worse.
The spelling of English definitely doesn't give enough clues about how a word is pronounced.
Me, and millions of other speakers of English as a second language, will vehemently disagree with that point.
The rest of your comment reads like a detailed attempt at rationalization of this untrue affirmation.
As a counterargument, take Spanish. Spanish is not younger than English, pronunciation has diverged and for example someone from Cuba and someone from Argentina pronounce many words differently.
The Spanish-speaking world is by no means small, or homogeneous.
And we absorb loanwords like madmen. Mostly from English, but also French, Japanese, Italian, etc.
The point is: Spanish is a much more phonetic language in its written form than English, so much that we have no spelling bees.
English simply fucked up itself with the great vowel shift, that's all.
Spanish is in fact younger. The language was standardized and normalized by royal edict about 500 years ago. While strongly based on Castilliano, it was not the same. "Spanish" as a single cohesive, consistent language did not exist before then in Spain or anywhere else.
By comparison, the rules and structures of English (such as they are) were not altered significantly following the great vowel shift in Chaucer's time. Mostly minor spelling changes and word choice.
All languages adopt foreign words unless there is an active body attempting to prevent it, such as the French Language Academy.
French words are not however just loaned to English. It was thoroughly baked in following the Battle of Hastings in 1066, when the nobility all spoke French for hundreds of years. Basically every "fancy" word in English came directly from French while "plain" words came from Anglo Saxon (Germanic) or other related sources. Incarcerated vs jailed. Debris vs trash. Magnificent vs great. "The player regarded his opponent." vs. "The player looked at his opponent." (French for "He looks" is "Il regarde".
The great vowel shift didn't mess up English; the lack of concerted normalization of English is what did it in. English is the greatest pragmatist without design of all world languages.
The usual argument against spelling reform is that it isn't possible to do it in a way that is compatible with the language of more than one region. For example, in Australian English they have a system of phonemic vowel length. This does not exist in other varieties of English, so the options you have in a spelling reform are (1) ignore the Australians and set spellings that are ambiguous in Australia, or (2) placate the Australians and include their vowels in the reformed spelling system, despite the fact that this leaves everyone else in the world mystified as to why certain words are spelled with doubled vowels and certain words aren't.
Start small, and use compromises. Don't try to be completely phonetic, which won't work for the reasons you mentioned.
You can start by undoing misguided spelling reforms of the past. "Debt" used to be spelled "det" but due to incorrectly inferred etymology it was changed to be non-phonetic. There are many words like these.
Then look for major inconsistencies where a cluster of letters is pronounced more than one way, and simplify one of them. For example, "ough" is pronounced as in "tough" more often than as in "though". Change "tough" to be spelled as "tuff" and "rough" as "ruff".
Going further, embrace text/informal writing and use tho, altho, nite, tonite, etc. Although the last two are not necessary since "ight" is pretty consistent. Keep common clusters of letters so that it still looks like English. Do it in in stages over a 100 years , making changes every 15 years or so. I'm mostly aiming at ease of reading vs ease of writing.
Every other major language had a recognized central authority to do its work. Spanish, French, written Chinese, etc. all had a monarchy/dictatorship of some sort to mandate the change and enforce its use.
England could have done it perhaps in Shakespeare's time or shortly thereafter, but once English spread across the globe in its modern (lack of) form with no recognized central authority with the power to force the change, it's not going to happen.
You couldn't get three states in the United States to agree on a universal spelling/pronunciation let alone the three countries in the United Kingdom. You think you'll have any more success over continents and across oceans?
> Spanish, French, written Chinese, etc. all had a monarchy/dictatorship of some sort to mandate the change and enforce its use.
There is no central authority over the Spanish language since the days of Bolivar and San Martin (1810s or so). Modern e.g. Argentinians would laugh at the idea that Real Academia Española has any say on how they should use their language. And indeed, there are differences not just in vocabulary and pronunciation, but also in grammar: "vos hablás" instead of "tú hablas".
Nevertheless, I can pick pretty much any written Spanish word and know how it sounds both in European and Argentinian Spanish.
It is specifically English which failed at the task of not being like Chinese.
Well, that’s a strange statement. Hangul is not just better by accident, it’s designed to be an advanced phonetic system making it possible to write many languages. You can learn in a few evenings, no need to know Korean, and you will be able to read Korean perfectly out loud without understanding what you are saying.
Hangul is phonetic, but doesn't have the capability to represent all phonetic sounds of a language. For example, Hindi has 4 distinct letters and consequently sounds for the each of D and T (D: ड ढ द ध, T: ट ठ त थ), which all correspond to the single Hangul letter diot (ㄷ). I have Korean friends who write their names in the Chinese script because they don't have the necessary letters to represent the sounds.
I don't think that's right. One example would be the words with the same spelling which are pronounced differently depending on meaning (e.g. dragonfly and sleeping spot), you have to know what you are saying to pronounce it correctly.
bluesmoon is right. Hangul doesn't solve all problems ever, anyways, here is some miscellaneous trivia. I have Korean friends. You're welcome Max-q. Please don't try to appreciate things around bluesmoon. You know how they get.
> It is "a guess" at best, and that guess won't be correct most of the time, unless you know the word already. And when you don't, you'll be dealing with all kinds of Cansas/Arcansas and although/drought/through/bought/cough/enough most of the time.
"Most of the time" is an exaggeration. English is (sadly) less strictly phonetic than many other languages, but still highly phonetic. Nearly every word in your own comment can be pronounced phonetically.
"Most" like "cost", or like "ghost?" Also, only now I checked the transcription for "exaggeration", and "gg" is not "g", like in "blogger", but ʤ like in "Jason". TIL.
If this is not "most of the time", than I don't know what is.
> In e.g. Russian or German, you can read the word from the way it is written and maybe miss the accent.
OK, but... the position of the word stress in Russian radically alters the pronunciation of all the vowels in the word. Missing the stress means mangling the whole word. That's not something to just dismiss.
I wasn't claiming English is the best language. I was saying non pictographic languages are one of humanity's most important inventions, which is one reason they've spread so rapidly everywhere.
Too bad non pictographic languages weren't paired with simple orthogonal grammars and consistent spelling rules. Learning different languages always feel like choosing whether I want to beat myself up with my left fist, my right fist, or my feet.
English has had a long trip to the language it is today. It doesn't help that at the latter stages of its development writers disagreed on or disregarded the rules of spelling.
It's a necessary evil owing to the large English lexicon filled with homophones. The Japanese stick to their ponderous use of Chinese characters for similar reasons.
> It's a necessary evil owing to the large English lexicon filled with homophones. The Japanese stick to their ponderous use of Chinese characters for similar reasons.
This is a common and incredibly stupid argument. Note that it immediately implies that oral communication in English and Japanese is impossible.
Early video games didn't have the memory available to render text in kanji and used kana exclusively. This caused zero problems.
There's something to that argument in Japanese. According to [1] Japanese has 643 distinct syllables, while English has about 6949.
There's a lot more context in speech and video games and long-form writing than in random writing and signs. It's virtually impossible to convey a meaning to a product or company name without using kanji.
I was originally thinking about names that have intended meanings "Target", "Burger King", "Taco bell", "Pager Duty", "DuckDuckGo", "Texas Instruments", "Aperture Laboratories" etc.
I am responding to your comment that oral communication is impossible because of homonyms. I am not covering the difference between oral and written communication.
You are right. When years ago apple was said to introduce "emoji", the arstechnica article I was reading was explaining what the hell emojis are.
They were like " it is a pictographical language like Chinese or hieroglyphic where each "idea" is represented by a single picture" and I simply could not wrap my head around it...
Do I have to learn a new language altogether? How ?
Will it fit on a keyboard? How many ideas can there be?
What if I have to say something longer?
What if I have to say a difficult concept?
Languages have different dimensions, including spelling, pronunciation, conjugation, grammar. English is moderately easy in spelling and pronunciation, but with exceptions and exceptions to the exceptions, it is harder than say Korean. Mandarin has more difficult spelling and pronunciation than English, but the low number of conjugations and tenses makes it much easier grammatically than English.
My understanding is that hieroglyphics can be read and written in either direction, and that the animal characters in particular give it away, if they're face right you read from the right and vice versa.
Yes, and there are some inscriptions where this is used, for example in "speech bubbles", where two figures facing each other on a wall talk to each other, with the texts flowing in different directions.
I wonder if this horizontal glyph direction has some sort of meaning lost to the sands of time. Armchair speculating outloud, maybe it’s not purely aesthetic and could imply some sort of past/future tense?
I don't think it does. Chinese, Japanese and Korean had been using vertical writing for centuries, only switching to horizontal ones around 20th century for interoperability with Western writing (such as math or chemical formulae).
Mongolian script, from the link presented here, has actually switched from being horizontal to being vertical (under influence of Chinese).
I like that. Mine is boustrophedon. When you get to the end of a line, you continue the next line starting at the same end. I know the ancient Greeks used it. I don't know who else. I keep pondering how hard it would be to write a text editor that handled that correctly.
It works fine with all of them. It's true that some letters are mirrored forms of other letters, but that doesn't leave any ambiguity - the form of the letter is oriented to the direction of reading, so "b" is a B when you're reading left-to-right and it's a D when you're reading right-to-left.
I'm not an expert on alphabetization, but AFAIK kids actually have some trouble getting the letters "the right way round", I think especially if they start very early. They might be learning the abstract shape first and the learn to force it into the self-relative forms like always-left-to-right. Which kind of makes sense, since objects in nature are usually encountered from all sides, orientation is rarely valuable. So in that sense I'm not convinced it's really an expense to have to learn it. And anecdotally, my son when he was 3-4, when presented with a grid of items would tend to go over it row by row in alternative directions, like writing in boustrophedon. And as you say it would also make very long lines of text more readable - I think Greek inscriptions often have ludicrous line lengths, like several meters. So there it's not just your eyeballs that are jumping, you actually have to walk back to the start of the next line!
kids are excellent at picking information because their brains by default will attempt "wild" interpretations of the same information. Their brains are the perfect startup in a way, in that they fail quick, they fail often , and they learn immediately.
This is also why its hard to do magic tricks with young kids. They will tend to be looking at all the wrong spots. Their brain doesn't pick up on attempted misdirection, it just decide to make a new test happen from a different vantage point.
> speed up reading as the eyeballs don't need to jump across the page to start a new line :-)
Reminds me of dot matrix printers... some could write lines from right to left without needing to go back to start of line, thus alternating directions.
As a kid I thought if i write English in a mirrored way i.e. right to left, & mirrored, it would be my code script, nobody else can read it. People read it very easily.
Not just smudging. The entire mechanical act of writing (and everything) is optimized for left handed operation being the mirror image of right-handed operation, since left is mirror image of right.
"At the one-time expense of having to learn to recognize letters and words both ways"
That is a very expensive expense, though. And the result might still be worse.
I can quickread a page in a couple of seconds, because my brain memorized the shape of the words and even sentences. It took me years of lots of reading to achieve that.
I am not sure if my brain could handle the double amount of shapes, because this is in effect what would be needed.
And eye movement is very quick. But feel free to give the experiment a shot and share results.
(it should be trivial to write a script that rearranges text that way)
> That is a very expensive expense, though. And the result might still be worse.
That's entirely possible but it is hard to tell without going through the entire learning process. There might be a lot of redundancy (as we can quickly recognize mirror shapes) which if tapped at an early age might make it actually a trivial "add-on".
Anecdotally you can learn within minutes to slowly parse script in reverse order. Whether you can ever get to the same speed is not clear. We do know that some cultures did use alternating script (so its clearly not impossible) but we also know that they abandoned it in the end - so there might be some disadvantages.
Maybe the reason for eventually adopting uniform LR or RL instead or alternating is not the difficulty of mastering mirror versions, but being able to quickly start reading from any line on a page. For example finding the spot where you left reading, or scanning to find a relevant part. For this task the alternating form is actually less efficient as you need to jump back and forth as you go down (or up :-) the page.
It shouldn't be too hard to make a chrome pluggin to render comment threads like this in alternative forward and mirror / backward lines. As you say reading mirror writing isn't too hard so you could sort of slowly get good at it while wasting time on HN anyway. Would be a fun silly project might give it a go.
Hangul in general is pretty smart in general. You can get the hang of it in an afternoon, which is something you cannot say about the Korean language in general.
I'm guessing it was top to bottom and then during the modernization process, left to right was added? It's smart that both forms are allowed though as I could imagine modifying a written language takes many years and massive public effort.
Yep, it used to be top to bottom, and the columns were arranged right to left. As a side effect of this recent transition, it's not particularly difficult to read Korean right to left, either.
It's the same in Chinese and Japanese. It helps a lot that the letters are designed fit into individual square blocks. The blocks can be arranged any way you want. There have been internet memes, for example, written to mean one thing when you read left to right and a completely different thing top to bottom.
But yes, Chinese was written top down, right to left. The PRC basically switched over to left-right, top-bottom right away (it kind of went hand in hand with the simplification project). Taiwan for example kept the traditional format for a lot longer.
When I was learning Mandarin in the late 90s, all our imported material from Taiwan was still top-down, right to left.
The traditional way is vertically, indeed, but on occasions you had to write horizontally, which was then usually also done right to left (can still be seen here and there, as I mentioned in my previous comment).
> The traditional way is vertically, indeed, but on occasions you had to write horizontally
There's not really a distinction. Chinese was written in columns from right to left. When the columns were one character long, they were still columns.
To distinguish horizontal writing from vertical writing, you'd need a writing sample that had multiple columns and also multiple rows. (Because, as noted above, there's no way to tell the difference between 1 row of 5 characters vs 5 columns of 1 character each.) As far as I'm aware, traditional Chinese writing is fully accounted for by the theory that it was always written in columns and never in rows.
On the other hand, the Taiwanese newspaper isn't making a great case: the "mixture of approaches" used in the headlines are a couple vertical headlines going top down, and several horizontal headings, including the primary headline "Michael Jackson、arrives!", which all go left-to-right. The body text in the infoboxes in the top left and right corners of the page also goes from left to right, though it appears to be true that the article text is in columns. The name of the newspaper (top center) is also printed left-to-right.
At least for Korean, it was right to left only when written top to bottom. Then it changed to left to right. It's never been right to left horizontally. I think it's the same with Chinese. I'm not sure about Japanese.
I've read that there are Arabic-Chinese dictionaries where Chinese is written from right to left to match Arabic direction of writing, but I don't know how common this is.
Do the individual syllables also reverse direction? They're normally read left to right and top to bottom. I'd imagine that they're taken in as complete syllables by readers rather than read sound-by-sound, so they maintain left-to-right.
This seems pretty efficient as there's no deadheading to get back to the other end of the line. When doing puzzles like word searches or scanning things laid out in grids like news article headlines, I do this l2r->r2l type of scanning. I've even caught myself using t2b->b2t scanning as well in these types of situations. It's just much more efficient
But left-to-right kinda is a law of nature: most people are right-handed, and to avoid messing with previously written glyphs it is natural to move to the right.
There’s also scripts written bottom to top (Libyc), and even stranger scripts which are written and read in different directions (Hanunó'o is generally written bottom to top — carved away from the writer really — but read left to right).
As a native arabic reader, Mongolian gives me headaches. My brain keeps seeing it as an unreadable arabic script rotated 45 degrees to the left. (It also turns out it does have some arabic influence[0])
Not-native Arabic reader here. To my eyes, it pretty clearly has a "baseline" that, if you tilted the text 45° to the right, would run along the "bottom". With this in mind, the similarity of many characters and ligatures to those in Arabic is striking.
Yes and right when my brain thinks it found something it could make sense of, my head tries intuitively to tilt to the left and I have to forcefully resist it.
Incidentally, having listened to a few clips of the language, it sounds like it has a slight Arabic tinge in some words. And otherwise reminds me of Russian, and sometimes Hangul.
No kidding! At some point Genghis Khan invaded Afghanistan. Over the next century Pax Mongolica made it as far as Egypt. Conquered swathes of Persia, felt cute, sacked Baghdad. Just Mongol things.
Splintered into a bunch of Khanates that started fighting each other..
Arguably they fell apart because they picked up so many scripts and cultural and religious influences the different types of Mongols could no longer communicate or tolerate one another. Then the bubonic plague came and they became insular again instead of expansionist.
Indeed. The fall of Baghdad [0] during that century at the hand of Hulagu Khan[1], the grandson of Gengis Khan, is thought to be a critical turning point that ended the islamic golden age and drove the eastern islamic caliphate to a dark age Iraq and other descendant countries never fully recovered from.
<graphic warning> According to some accounts, Hulagu cut open the belly of the Caliph Al-Musta'sim, pulled his guts and left them on top of the caliph's head to drip while he was slowly dying. Some other accounts relate that he was killed by horse trampling wrapper in a rug.</graphic warning>
It's also fascinating that Mongols, with all their mighty army, would settle in a land upon invading it, marrying into the locals, adopting their religion and traditions. Some modern Russian, Turk and Persian populations have this "reverse influence" from past Mongol invasions and admixture with actual Mongol people. Tatars[2] are a notable example, a Russo-Turko-Mongol population descending from Golden Horde troops who settled around the Volga (as everything in ethnographics, this is contested).
The Mongoles did some horrible things. In the Shahr-e-Gholghola, when the grandson of Gengis Khan was killed, he ordered that everyone in the city be killed, including children in cribs. As if that was not enough, they left the city and returned a few days to kill any survivors.
"Arguably they fell apart because they picked up so many scripts and cultural and religious influences the different types of Mongols could no longer communicate or tolerate one another. "
Interesting thought and it certainly had influence, but I would argue that the trope that one strong ruler conquers a big kingdom, but it doesn't stay united, because his heirs cannot settle on the next great king, is a quite common and often repeated one.
Unfortunately, touchpad scrolling on this specific website is basically unusable for what I believe is a very large fraction of laptop users because:
(a) it does scrolljacking, which cannot be done well on the web (it doesn’t expose the right primitives) so sites should never do it¹ but find some other way;
(b) its scrolljacking implementation is considerably worse than is possible; and
(c) it intercepts all scrolling, rather than leaving horizontal scrolling alone and only redirecting vertical scrolling.
Fortunately, I browse the web with JavaScript disabled by default, so I’m fine other than when I’m checking this out!
(I noted this a couple of years back in https://news.ycombinator.com/item?id=27758336, and I don’t think the site’s implementation has changed at all since then; Firefox exhibits the same symptoms, Chromium has changed to behave somewhat more like Firefox now.)
—⁂—
¹ Sites, as distinct from apps; there are a few sorts of apps that can’t avoid it and must do the best they can, e.g. maps; incidentally, Google Maps has the only consistently-decent scrolljacking implementation for web-based maps that I’ve ever found.
Probably, the person you are responding to does not understand that "mng" in the URL means "Mongolian written in the Mongolian script" and did not guess either that the letters "MN" at bottom left meant "Mongolian written in the Cyrillic script".
Fair enough, that makes sense. I’d clocked there was a language toggle to the English version but didn’t think to remove the path. Thanks for the heads up!
Don't worry, they will learn as quickly as they quickly learned the Cyrillic alphabet, which appeared in Mongolia in 1940 only. And for this it will not be necessary to kill as many people in the "purges" as they were killed by the "Choibalsan's troikas".
I was fascinated to learn there are more Mongolians living in China than in Mongolia.
They still learn the traditional Mongolian script.
There was some uproar a few years back when the government required core classes like math and science to be taught in Chinese, but the rest is still taught in Mongolian.
Mongolian script is also printed on Chinese currency, in addition to Tibetan, Uyghur, and Zhuang.
> no purpose other than grazing the dictators’ testies
You do realise cyrillic script in Mongolia is a direct consequence of Soviet history-rewriting "one russian man" policy? And that current effort in post-soviet countries to move away from cyrillic and russian is mostly driven by security - as in one less reasons for Russia to come "save their brothers".
Isolating your country language-wise does have some benefits. For example, it tends to create cultural unity and prevents parts of your country breaking off and joining a neighbouring country.
For example, in the USA, the english vs spanish divide pretty much aligns with the US/mexico border. If both countries used the same language, the border could be more easily moved by groups friendly to one government over another. The effect could be strengthened by requiring english/spanish tests at the border, and preventing teaching in the 'wrong' language.
It can also prevent emigration of the smartest people.
> Isolating your country language-wise does have some benefits. For example, it tends to create cultural unity and prevents parts of your country breaking off and joining a neighbouring country. […] If both countries used the same language, the border could be more easily moved by groups friendly to one government over another.
Why then have no serious attempts occurred by parts of Canada to join the US or vice versa? Most of both countries speaks English and only English, with extreme cultural overlap and a huge shared border.
I don’t think most of the southern US would want to deal join the mess that is northern Mexico right now, nor would the cartels want to release northern Mexico into the relative safety of the southern US. That matters far more than the different majority language across the US-Mexico border.
> For example, in the USA, the english vs spanish divide pretty much aligns with the US/mexico border.
If you’re talking only about the number 1 language in each country, then sure, but otherwise you’re vastly underestimating how much Spanish there is in the US, especially in states like California, New York, Texas, and Florida among others.
It’s easy for anglophones to ignore “por español, oprima dos” in phone menus or to tune out the daily occurrences of Spanish one passes on the streets or doesn’t quite hear clearly from the front in restaurant kitchens, but it’s all around us to the extent that Spanish-speaking visitors can get around fine with limited or no English in some major cities - and that’s getting only more true, not less.
The US has more Spanish speakers including those of limited competency than any other country except Mexico, including Spain; if you restrict to native-level speakers, the US appears to be number 5 on the global list, behind Mexico, Colombia, Argentina, and remarkably narrowly behind Spain.
The same source notes the continuing growth of Spanish language and Hispanic origins in the US. It predicts that by 2060 the US will be the second biggest Spanish-speaking country (I presume they mean natively or at a native level), and that 27.5% of the US will be of Hispanic origin.
To be clear, I don’t mind the growth of Spanish in the US and don’t view English as inherent to the American identity, even though I’m a native anglophone. Hell, German was pretty major in the US too before the world wars last century, and my immigrant great-grandparents probably spoke Yiddish better than English. The foundation of the US is not about linguistics, nor ethnicity.
I am not sure what is harder: learn separate characters for words or learn the correct spelling for words? Especially with English where there is a big gap between spelling and pronouciation, learning the correct spelling for words takes a lot of memorization effort.
The fact that many adult cannot spell 100% correctly, proves that spelling is difficult.
Writing a language is always harder than reading. Many people rely on muscle memory when writing words. It might be that this works better for writing chinese characters than for words, which is more likely to fail when words contain multiple instances of characters.
It might also be the case that the number of strokes needed to write an average characters is about the same as writing an average word.
But there are many languages where words are (nearly always) written the way they are said. As a native Bulgarian I always found the concept of a spelling bee very odd. IMHO it's the best of both worlds but it only really works where accents are less of a thing.
Imperial measurements are a gigantic waste of human work too. Metric won
The US continues to use them though, it's part of their culture. We don't need to optimise everything, and the world would be a very sad place if we did.
I've picked up woodworking and imperial inch fractions are a much better mental model for simple math (doubling/halving/dividing lengths, centering things etc) than arbitrary mm values.
There's also a thing about the inch being a (subjectively) good "bite size" unit. 1cm is too small, 10cm is way too big.
I'm also French and I live in the US. What a load of crap. You're telling me it's easier for you to double "6 and 3/4 inch" than "17.14 cm"? I balk every time I have to do the mental gymnastics.
"Okay, 6+3/4 inches doubled, that's 12+6/4 inches. But 6/4 is 1+2/4 which is 1+1/2, so 13+1/2 inches, or 1ft 1+1/2in".
If you've ever done woodworking, you'd appreciate the imperial system, especially when working with kerf size and whatnot. The imperial system was literally made for that kind of application. Rather, not made, but it emerged.
The imperial system emerged piecemeal as a series of domain-specific measurements, where each unit conveyed deeper meaning beyond rote volume, distance, etc. For example, an acre means much more than 43,560 feet squared. It means "roughly the amount of land that a pair of oxen can plow in a day". A nice domain-specific measurement that communicates something useful to the experts of that domain, in this case, plowmen, farmers, and lords of the manor.
With inches, an inch is about the length of your thumb. Imagine doing woodworking and measuring in thumbs - it's right there in front of you, easy to conceptualize and work with, an intuitive "bite-size" unit of measurement. Fractional centimeters aren't as intuitive to work with and conceptualize. 6+3/4 inches is a lot more workable than 17.14cm.
I have dabbled in woodworking. I still stick to metric. You can spend all day rationalizing why the system you've been immersed in since childhood is more intuitive. In the end, it's more intuitive to you because it's what you're used to.
Your example is a prime one. I'm not used to measure things with my thumbs, so if you told me that something is ten thumbs wide, I'd have to think some time before I could make a mental picture of it, and an inaccurate one to boot. I'm used to measure things with centimeters, so I immediately know what 10 cm looks like.
> Fractional centimeters aren't as intuitive to work with and conceptualize.
To you they're not. To people used to it, they are.
Pretty much, the same way fractions carry over inches as decimals carry over the next power of ten, and as a developer I find powers of two more intuitive.
Example: I mostly work with 3/4" thick material, which is a breeze to divide into 3 for 1/4" mortice and tenons. The equivalent 19mm in that respect is a bit trickier, though fortunately EU 3/4 lumber tends to be only 18mm thick.
Everyone loves to rip on the US as one of the only countries that “won’t use metric” but I wonder how many places officially adopt metric but traditional measures are still in common use. In Taiwan it’s very common to buy things in 斤 jin, aka catty. It’s 600 g in Taiwan and slightly less or more in other Sinophone countries. Housing is also measured in 坪 píng, which is the square area of a standard tatami matt. I think Japan uses this too because in TW it’s a legacy of Japanese colonialism.
For mainland China, a 斤 is 500g. Very common unit of weight.
Housing would be measured in 平米, square meters. It's pretty much impossible to understand that one as anything other than an adoption of the foreign norm. (Similarly for 斤, set at half a kilogram to fall within the range of traditional use while still fitting seamlessly into the metric system. But wholesale adoption there would mean measuring weights in 公斤, kilograms, which isn't done much.)
...are you under the impression that Mongol bichig is a script similar to Chinese characters? What issues do you think it has that Cyrillic doesn't have?
I still dont understand how most site in 2023 cant handle HN traffic. Especially when they are static pages. The HN burst of traffic isn't as high as most people imagine.
Interesting to note numerals are still Arabic, but written vertically. Does that mean that in school Mongolian kids learn to write digits sideways? Would be pretty cool :D
Some time ago I lived with a Mongolian student for a while and I was really surprised to find out that Cyrillic is the default alphabet in the country.
My language is written in Cyrillic and while most Cyrillic languages come from the same Slavic language family, Mongolian has very little similarities with the rest.
The same used to be true of the Romanian Principalities until the middle of the 19th century, when we switched to Latin alphabet in order to underline our Romance-language roots and to culturally distance ourselves from the expanding Tsarist Empire.
Of course, the Soviet Republic of Moldova used the Cyrillic writing for Romanian throughout most of its existence, the people over there switching to Latin alphabet in the dying days of the Soviet Union was a prelude to their independence (I have two books in Romanian and using Latin alphabet published in the Soviet Republic of Moldova towards the end of the ‘80s - 1990, priced in rubles and all, really cool).
I love how this makes the usage of screen real-estate very efficient. You can some entire articles without having to scroll the page. I also love how landscape images fit neatly in this configuration.
It is very tempting to try to make a website that uses this configuration for english text.
Also, even though it is the very first time I see this script, I can tell that the website is very well done (well, it's the website of the president of the country, but still).
When I loaded the page, the pagination numbers were in English, but the page text was in Mongolian script. About 2 seconds later, the page reloaded and showed everything in Mongolian.
to be fair, google translate misidentifies a lot of input if instructions are unclear.
And I think it's acceptable that they do not offer transcription for all the foreign scripts. Though helpful it would be, it's also very likely to make many mistakes.
It doesn't fully work on my phone, which really makes me wonder how easy it would be to use digital devices as a Mongolian, who only speaks Mongolian, and no other language.
writing-mode support is pretty good these days. Here is another website in the wild using it for vertical text, mixed with horizontal text: http://ko.scp-wiki.net/gumiho
I wish it was easy to render western text to multiple columns that are fit to the screen. Reading like a multicolumn paper newspaper and scrolling horizontally. I think this shows that it would be pleasant to read text on the web this way.
Does it cause for anyone else what it does for me -- the whole screen "vibrating" when you reach the limits of the horizontal scroll, or somewhat even while you're scrolling?
Copy-pasting it into GPT-4 and asking for a translation:
> "Mongolia's heroic history of the ancient period, from the time when heroes ruled the land, has left many great legacies. Among them, the unparalleled courage and power of the heroes of that time have been passed down through generations. Today, we continue to celebrate their extraordinary achievements and admire their incredible strength, while also learning from their wisdom and following their footsteps.
> "Mongolia's heroic history spans over 80 years, during which many heroes have emerged and made their mark on the nation."
Unbelievable. Google's slipping hard on translation.
Монгол улс хөгжлийн төслийг эрхэм хуваарь болон сан 80 хубитай ийм дотоодын төсөл дээр ажиллаж байгаа уулзалт болно.
In English, the translation is:
The Mongolian state is working on certain publications and broadcasting stations related to their province in the area they are visiting. These activists are researching and aiming to innovate, updating their important schedule and planning, and increasing their salary. They introduce the help they provide in the aspect of the living standards where they are working.
Is the Mongolian state working on an internal project with an 80-million budget for development with an important schedule and planning?
---snap---
edit: I pasted it into a second chat and then it gave me:
---snip2---
The Mongolian script you've provided appears to be in Classical Mongolian, which is written vertically. Here is my attempt at translating the text into English:
The Mongolian nation has a long and rich history, and the customs and culture of the people have been passed down from generation to generation. The land is vast and diverse, with many different landscapes and natural wonders to explore. Over the centuries, the Mongolian people have overcome many challenges and have continued to adapt and grow, forging a strong and unique identity.
Mongolia has a proud heritage that dates back over 80 years, and the people have always been resilient and determined in the face of adversity.
To be fair, it's more about Google Translate straight up doesn't support Mongolian scripts than being this bad. It only supports Mongolian language in Cyrillic.
Classical Mongolian is actually not a straightforward 1-to-1 conversion, and it's not clear if Khalkha Mongolian and Classical Mongolian should be treated as the same language in Google (Classical Mongolian is a common writing language not just for Khalkha Mongolian used in Mongolia, but also for Buryat and, but in Cyrillic those two languages are written differently).
E.g. the first line of a poem from linguamongolia.com, "saiqan časutu čağan ağulan-dur" (see http://www.linguamongolia.com/reso1.html , White Mountains document for original script) would be written "сайхан цаст цагаан уулд" (saihan cast cağan uuld) in Khalkha Mongolian orthography, if I'm not mistaken.
But then, sometimes Google Translate is happily combining two languages. E.g. it can translate from Crimean Tatar, but it will detect it as Tatar, even though it's a different language...
Oh, I recently moved to Israel, and at first was shocked with how much worse design in general is. Like, typography, ads and of course UI. There are maybe 3-4 common fonts used everywhere, and I think it's a common problem for "rare" scripts. It seems you need some "critical mass" of visual content to come up with good design practices and figure out what looks good in your cultural landscape.
We tend to assume that left-to-right script is a law of nature but it is just one of many variations that have been invented and used across space and time. Right-to-left (Arab / Hebrew) [2] is well known but a most intriguing one used in antiquity by Greeks and others is Boustrophedon (alternating from left-to-right / right-to-left).[3]
Boustrophedon mode is in one sense the optimal script form. At the one-time expense of having to learn to recognize letters and words both ways one can then (in principle) speed up reading as the eyeballs don't need to jump across the page to start a new line :-)
[1] https://www.w3.org/International/mlreq/
[2] https://www.w3.org/International/questions/qa-scripts
[3] https://en.wikipedia.org/wiki/Boustrophedon