Wikipedia:Reference desk/Language

Welcome to the language section
of the Wikipedia reference desk.

skip to bottom

Select a section:

• Computing
• Entertainment
• Humanities
• Language
• Mathematics
• Science
• Miscellaneous
• Archives

Want a faster answer?

Main page: Help searching Wikipedia

   

How can I get my question answered?

• Select the section of the desk that best fits the general topic of your question (see the navigation column to the right).
• Post your question to only one section, providing a short header that gives the topic of your question.
• Type '~~~~' (that is, four tilde characters) at the end – this signs and dates your contribution so we know who wrote what and when.
• Don't post personal contact information – it will be removed. Any answers will be provided here.
• Please be as specific as possible, and include all relevant context – the usefulness of answers may depend on the context.
• Note:
  • We don't answer (and may remove) questions that require medical diagnosis or legal advice.
  • We don't answer requests for opinions, predictions or debate.
  • We don't do your homework for you, though we'll help you past the stuck point.
  • We don't conduct original research or provide a free source of ideas, but we'll help you find information you need.

Ready? Ask a new question!

How do I answer a question?

Main page: Wikipedia:Reference desk/Guidelines

• The best answers address the question directly, and back up facts with wikilinks and links to sources. Do not edit others' comments and do not give any medical or legal advice.

See also:

• Teahouse
• Help desk
• Village pump
• Help manual

June 9

Uddannelseskabale

In UCL University College, there is a dead reference from the college website with the title "Danmarkshistoriens største uddannelseskabale går op i Odense". What does this mean? "The biggest education cabal in Danish history is taking place in Odense" is obviously wrong. An internet search finds a few more instances of uddannelseskabale, but I still have little idea what it means. TSventon (talk) 09:17, 9 June 2023 (UTC)

It certainly sounds like it's supporting the claim that cites it, about consolidat[ing] six separate sites in Odense. Folly Mox (talk) 09:59, 9 June 2023 (UTC)

"Kabale" is also the Danish word for the card game patience/solitaire. One use of the word "uddannelseskabale" seems to refer to the allocation of study places, e.g here. My guess is that it is a metaphor for (re)allocating things. In this case sites from one university to another. -- Random person no 362478479 (talk) 10:10, 9 June 2023 (UTC)

Thank you both, the edit which added the reference in 2013 is here. I want to add an English translation of the title, possibly "The biggest educational development in Danish history is taking place in Odense", and am hoping that someone with a better knowledge of Danish, and/or a Danish dictionary can contribute. TSventon (talk) 10:17, 9 June 2023 (UTC)

According to Den Danske Ordbog, "kabale" could mean something like "complicated situation" or "quandary". I don't know if "education quandary" would fit in context? (That link given by Random... seems to indicate something like placing the pieces in a puzzle correctly.) 惑乱 Wakuran (talk) 11:46, 9 June 2023 (UTC)

The DDO adds "Se også puslespil" ("See also jigsaw puzzle"). I'd translate it here as "education puzzle".  --Lambiam 15:30, 9 June 2023 (UTC)

Thankyou all, so the translation is "The biggest education puzzle in Danish history is solved in Odense". I am not convinced that transferring a site between colleges in Odense was really "The biggest education puzzle in Danish history", but perhaps it seemed so to the college at the time. TSventon (talk) 16:16, 9 June 2023 (UTC)

I'd use "largest" rather than "biggest" and the present progressive: "The largest education puzzle in Danish history is being solved in Odense". Transferring six existing sites so as to merge them into an existing site elsewhere can be more of a puzzle than merely transferring a site. The headline may be the copy editor's, seeking an attention-grabbing line, rather than the college's.  --Lambiam 07:57, 10 June 2023 (UTC)

I think that makes sense. It can be seen as putting different pieces in place. I did some more googling just with "kabale" and I found a number of uses in sports regarding things like selecting players for a national team, deciding what position a new player in a team should take, and similar issues. That would fit the idea of putting together a puzzle by finding the right piece for the right place. The example of allocating study places can be thought of along the same lines. An alternative to "is being solved" could be "is being put together". -- Random person no 362478479 (talk) 18:10, 10 June 2023 (UTC)

The idiom is to put the pieces together, so if you use "being put together", the proper translation should be, "The pieces of the largest education puzzle in Danish history are being put together in Odense". Or you can say, "The largest education puzzle in Danish history is being pieced together in Odense".  --Lambiam 07:20, 12 June 2023 (UTC)

Two questions

1. Are there any words in Spanish which end in ll or ñ?
2. Are there any verbs in German that have identical present and imperfect form (like English put, which dets neither ablaut not -ed suffix im imperfect)?--40bus (talk) 14:48, 9 June 2023 (UTC)

Googling the subject, it appears the only Spanish words ending in ll are in, or borrowed from, Catalan. As for ending with ñ, it shows two examples: macuñ and ñuquiñ. ←Baseball Bugs ^{What's up, Doc?} carrots→ 15:42, 9 June 2023 (UTC)

Maybe: baby doll, güell, Forcall, Masamagrell, quiquill, pinball, Ullastrell (some are placenames). Some sites list these, but I don't know if they are real words: amomaricamañ, cholcheñ, Cumiñ, macuñ, Mucuñ, Nimañ, ñuquiñ. 87.13.136.172 (talk) 17:39, 9 June 2023 (UTC)

June 10

Book translation for Roger Masson

Hi, could somebody please idiomatic translate this book title from German to English. .

"Nationalsozialistische Großraumordnung : Die Konstruktion einer "deutschen Monroe-Doktrin"

Its for the Roger Masson article ref. I not sure what "Großraumordnung" means. Thanks scope_creep^Talk 09:08, 10 June 2023 (UTC)

This article has "the order of the Great Area". Make of that what you will. Alansplodge (talk) 11:36, 10 June 2023 (UTC)

Hi @Alansplodge: Thanks for that. I'll read up on it. scope_creep^Talk 11:42, 10 June 2023 (UTC)

Some elucidation;

Schmitt’s idea of Großraum — a greater territorial space or a pan-region — as the elementary building block for an anti-cosmopolitan, anti-universal organization of the international order based on a plurality of co-existing Großräume, each one under the leadership of an imperial nation.

DECISIONS AND INDECISIONS: Political and Intellectual Receptions of Carl Schmitt

Alansplodge (talk) 11:44, 10 June 2023 (UTC)

Based on the Monroe Doctrine, "Großraumordnung" could be translated sphere of influence. TSventon (talk) 12:03, 10 June 2023 (UTC)

Beyond the Conceivable Studies on Germany, Nazism, and the Holocaust (Dan Diner, 2000, p45) mentions "regional hegemony in the form of a greater territorial order [Großraumordnung]". TSventon (talk) 12:14, 10 June 2023 (UTC)

One of the synonyms for the German word Ordnung is the German word (or possibly loanword) Organisation, so you can see how the meaning developed. 2A00:23C3:FB81:A501:24FC:4B46:8DAC:E612 (talk) 12:19, 10 June 2023 (UTC)

I think Ordnung here has the same sense as English order in the translation "New Order" of the Nazi concept known as Neuordnung in German, or as in "New World Order".  --Lambiam 14:40, 10 June 2023 (UTC)

So it could something like "Nazi New World Order:The creation of the German Monroe Doctrine" or possibly "Nazi Planned Regional Hegemony:The creation of the German Monroe Doctrine"? scope_creep^Talk 15:29, 10 June 2023 (UTC)

Schmitt 2011 has

"notably his 1939 Völkerrechtliche Großraumordnung mit Interventionsverbot für Raumfremde Mächte [The Order of Greater Spaces in International Law and the Prohibition of Intervention for Space-Alien Powers]. "The order of Greater Spaces". I'm not even what that means. Probably an article would be ideal here. scope_creep^Talk 15:38, 10 June 2023 (UTC)

Großraum just means "large area". In the context of these publications, we should think of really large areas, like even continents. German happily stacks words together to form compounds, which are sometimes not so easily translated (Großdruckbuchstabe, Großhändleraufschlag, Großvieheinheit). A reasonable translation of Großraumordnung is (IMO) "order of greater areas" or "order based on greater areas". (For the choice of "greater", compare Großdeutschland = Greater Germany.) If this translation is not immediately abundantly clear, it is something it has in common with the German word, which needs to be clarified by a context.  --Lambiam 18:00, 10 June 2023 (UTC)

I think the underlying idea is that a few great powers carve up the world and then basically leave each other alone, no interference, no collaboration, no "intermingling". I believe it goes beyond spheres of influence, it would probably be more like spheres of control, either in the form of giant empire states or great empire states with smaller vassal states with limited autonomy.

Is it at all an option to leave "Großraumordnung" untranslated? E.g. "National socialist Großraumordnung: The construction of a "German Monroe Doctrine".

You'll notice that I used "national socialist" instead of "Nazi" and "construction" instead of "development".

The word "Konstruktion" can , like "construction", refer both to the act or process or to the result of the process. I'm not familiar with the book so I can't say which meaning is more likely to be the intended one. If the subject of the book is how the doctrine was developed historically translating it as "development" is preferable. But if it focuses more on the content of the doctrine, i.e. on the "Großraumordnung" then it may refer to this order as a "Konstruktion".

The reason for using "national socialist" is mainly that it seems more fitting for academic discourse. At least in German historiography (I am less familiar with English language historiography in this field) the term "nationalsozialistisch" is usually preferred. Although there are exceptions, e.g. there is a paper by Dan Diner which is notorious for the fact that he switches from "nationalsozialistisch" to "nazi" half-way through. -- Random person no 362478479 (talk) 18:41, 10 June 2023 (UTC)

There is an article on pan-region, which seems to be Karl Haushofer's version of Großraum, but it only cites one source. TSventon (talk) 06:35, 11 June 2023 (UTC)

Another translation is "large-scale order" in The Administrative State (Armin von Bogdandy et al, 2017, p. 52). I am not sure that Großraumordnung needs an article, but a section like de:Carl Schmitt#Großraumordnung could be useful. TSventon (talk) 07:48, 11 June 2023 (UTC)

There seem to be a number of publications that translate "Großraum" as "great space" in the context of Schmitt: [1][2] and a handful that translate "Großraumordnung" as "order of great spaces"[3]. Given that that is a very literal translation that may indeed be the best option. -- Random person no 362478479 (talk) 11:25, 11 June 2023 (UTC)

Note that the English Wiktionary gives these senses for Großraum:

1. wider area; (of a city) metropolitan area

   Großraum London — Greater London

2. large room

The German Wiktionary gives the corresponding senses:

[1] zusammenhängendes, als Einheit verstandenes, größeres Gebiet

[2] großer Innenraum

Here the first sense applies, in translation, "coherent, larger area conceived of as a unit". Translating Raum as "area" in the context is fully justified and IMO preferable.  --Lambiam 19:54, 11 June 2023 (UTC)

I found examples where Schmitt's "Großraum" is translated as "great area". So both seem to be in use and you can chose whichever you prefer. -- Random person no 362478479 (talk) 16:52, 12 June 2023 (UTC)

Is it possible to make an attempt at a translation? scope_creep^Talk 12:16, 14 June 2023 (UTC)

"National socialist order of great areas: The development of a 'German Monroe Doctrine'"

Alternatives:

"nazi" instead of "national socialist"

"spaces" instead of "areas"

"construction" instead of "development"

Any combination of those should work. -- Random person no 362478479 (talk) 18:14, 14 June 2023 (UTC)

I think "National Socialist" is preferable to "Nazi", which initially was a pejorative for persons of the National Socialist persuasion. The sense of Raum here is a geographic territory, for which the polysemous term "space" is rarely used. I do prefer "construction" over "development", though. If the author had intended to describe a process of development, he would have used Entwicklung. Given the topic, it is more likely about how the concept was fashioned, like the term "construction" is used in "the construction of a national identity"[4] – creating something that did not exist before. The book is about the concept of a World order in terms of divvying up the World into a relatively small number of Großräume, constructed as a justification for the occupation of a large area by the Third Reich. One possibility is "order of great(er) areas"; another is "greater-area order". The latter feels better to me. All combined, throwing in a definite article to make it more idiomatic, The National Socialist greater-area order: The construction of a "German Monroe Doctrine".  --Lambiam 00:04, 15 June 2023 (UTC)

@Scope creep: Strongly disagree with "great area"; the sense of the word by itself or combined with city or small region names is closer to "Greater" as previously mentioned, in "Greater New York" and so on. However, that's not what it means here, because they are talking about at least Europe here, so in the two-word phrase in the OP, it means the "Nazi New World Order" (with or without 'World', but I like it with). That this is so can be seen in numerous articles that talk about Schmitt's Volkerrechtliche Großraumordnung (3rd. ed., 1941; also in English) which is the "New International Order". See for example, Peter Stirk's article "Carl Schmitt's 'Völkerrechtliche Grossraumordnung' " where he uses "Nazi New Order" (p. 358), and just plain "New Order" for short (sometimes lower case), after the original term has been introduced; or Gary Ulmen's "Toward a New World Order: Introduction to Schmitt" (1996). So, I'd go with "Nazi New [World] Order" the first time, and then maybe shorten it by dropping the "Nazi" on subsequent uses. Mathglot (talk) 01:29, 16 June 2023 (UTC)

I'll take a look at the jstor doc today. It really comes to either "The National Socialist greater-area order: The construction of a "German Monroe Doctrine" or "Nazi New Order" or possibly "National Socialist New Order..." The concept seems to be the same kind of encapsulation, the control of an area within a greater area. I've sent a service request to De Gruyter for a comment to determine if they can provide a translation, since they now own the publisher. scope_creep^Talk

June 11

Diphthong question

Do French and Swedish have any diphthongs? Is aï in French maïs diphthong or hiatus and are oi in French in voix and oj in Swedish pojke diphtongs or semivowels? --40bus (talk) 16:31, 11 June 2023 (UTC)

If I'm not mistaken, the traditional analysis of Standard Swedish is that it doesn't have diphtongs, and /Vj/ combinations always contain a semivowel. 惑乱 Wakuran (talk) 16:45, 11 June 2023 (UTC)

By the way, French 'oi' is generally pronounced as [wɑ], not [ɔɪ], it seems as you might not have been clear about it. (So yes, it's a semivowel.) 惑乱 Wakuran (talk) 17:23, 11 June 2023 (UTC)

I have been aware of this for a while, and my question about that is: can the [wɑ] be transcribed as [u̯ɑ]? --40bus (talk) 17:24, 12 June 2023 (UTC)

Wiktionary gives two pronunciations for maïs, one from Paris as /ma.is/, two syllables with a hiatus, and a variant from Toulouse as /majs/, a single syllable with a vowel followed by a semivowel. This combination also occurs in the standard pronunciation of French canaille (/ka.naj/), rail (/ʁaj/), travail (/tʁa.vaj/), and many other words. It is generally not considered a diphthong, and neither is /ɛj/ in abeille (/a.bɛj/), /ij/ in coquille (/kɔ.kij/) or /uj/ in ratatouille (/ʁa.ta.tuj/). When followed by a vowel, the vowel and semivowel happily part ways, taking up residence in separate syllables: railler (/ʁa.je/), rayon (/ʁɛ.jɔ̃/), papillon (/pa.pi.jɔ̃/), bouillon (/bu.jɔ̃/).  --Lambiam 20:24, 11 June 2023 (UTC)

Any sequence of a vowel and a semivowel (in either order) in the same syllable is a diphthong. Whether such a sequence is considered one phoneme or two depends on language (and analysis—it's even possible to analyze English as having no phonemic diphthongs). Nardog (talk) 00:53, 12 June 2023 (UTC)

Note, though, that – as reported on the French Wikipedia in the section Diphtongue § Existence des diphtongues en français moderne – there are other points of view.  --Lambiam 07:36, 12 June 2023 (UTC)

That section is all about whether French has phonemic diphthongs, and it says, just as I said, it can be analyzed that it does or that it doesn't. [je, ɥi, wa] are, from a cross-linguistic, phonetic point of view, unequivocally diphthongs, in that they stand in contrast to [i.e, y.i, u.a]. Whether that means it is reasonable to posit /je, ɥi, wa/ as distinct phonemes in French is a totally different matter. Nardog (talk) 08:15, 12 June 2023 (UTC)

It is a matter of which definition one prefers. To some authors only phonemic diphthongs are diphthongs; accidental juxtapositions do not qualify.^[5][6][7] Arguments for either choice can be given; neither is inherently superior.  --Lambiam 19:29, 12 June 2023 (UTC)

The extra dot in maïs, naïf, haïr signifies hiatus. —Tamfang (talk) 16:26, 12 June 2023 (UTC)

Which does not keep a Toulousian from pronouncing the ⟨aï⟩ in maïs as a vowel followed without hiatus by a semivowel.  --Lambiam 06:35, 13 June 2023 (UTC)

June 12

Syria, vs. Libya.

Is there any reasonable explanation for the order, of the second and fourth letters, that turns over, when Syria is replaced by Libya? Additionally, why is the way of spelling Libya/Kenya so different from the way of spelling more than twenty percent of the countries (all over the world), whose names end with "ia", rather than with "ya", including many Arabic country names, like Algeria, Mauritania, Saudi Arabia, Somalia, Syria, Tunisia?

2A06:C701:7456:CB00:7190:3751:4898:4134 (talk) 00:48, 12 June 2023 (UTC)

Have you read the "Etymology" sections in Libya and Syria? Libya's name came through Greek Λιβύη, and Greek υ (when not part of a diphthong) is usually transliterated as "y" (as in psyche, hyper-, etc.). Deor (talk) 01:28, 12 June 2023 (UTC)

if you can only answer one part of my whole question, it's quite legitimate, but I don't know why you had to change the last version of my question to an old one that only contained the part you wanted to answer, so I'm reverting it back to my recent version. 2A06:C701:7456:CB00:7190:3751:4898:4134 (talk) 04:06, 12 June 2023 (UTC)

Syria came from Ancient Greek Συρία. Libya is spelled with a ⟨y⟩ because it was spelled that way by the Ancient Romans^[8] (using the newly introduced letter Y to represent the Greek sound /y/) and there was no good reason to switch to a different spelling, just like we still write Dionysus and not Dionisus. The indigenous Kikamba name of Mount Kenya, after which the country was named, is Ki Nyaa, "Ostrich Mountain". Why should its spelling be homologized, diverging from its pronunciation /ˈkɛn.jə/, with etymologically unrelated country names? It does not make sense, and if it does not make sense, you must acquit.  --Lambiam 08:10, 12 June 2023 (UTC)

Yeah, 'i' and vocalic 'y' are pronounced identically in English, but in many other languages, that's just not the case, such as in Swedish Syrien [syːrɪ'ɛn] and Libyen [liːbʏ'ɛn]. (I'd assume that transcription should be mostly right, but I could be corrected.) 惑乱 Wakuran (talk) 11:14, 12 June 2023 (UTC)

"Why does this language do this?" type questions are basically unanswerable. That's just the way things happened to turn out. If you could go back and start over, the sequence of events (and thus the resulting language) would probably be quite different. --User:Khajidha (talk) (contributions) 15:20, 12 June 2023 (UTC)

As Stephen Jay Gould loved to point out in another context. —Tamfang (talk) 16:28, 12 June 2023 (UTC)

Yet, we seem to have the required three explanations now. I suppose the only remaining part is the regular English suffix -ia for country names, which comes from Latin -ia, where we can see that if there was a country of people whose defining characteristic was being absent, they would live in Absentia.  Card Zero  (talk) 16:58, 12 June 2023 (UTC)

Except that the explanations do not actually answer the question of "why". --User:Khajidha (talk) (contributions) 17:52, 12 June 2023 (UTC)

We don't seem to have an article on the why game, commonly used by small children to annoy their parents, but it's epistemologically interesting. How much of an explanation is a complete explanation? When should we be satisfied? Personally I'm satisfied with "because the Romans used y to represent Greek ῠ", and something about ostriches, but we could go on asking endless questions. This doesn't strike me as a reason to dissuade people from starting, just so long as they eventually feel happy and stop.  Card Zero  (talk) 18:00, 12 June 2023 (UTC)

Listen to Richard Feynman discussing why Aunt Minnie is in hospital: Richard Feynman. Why.  --Lambiam 06:28, 13 June 2023 (UTC)

I keep six honest serving-men... DuncanHill (talk) 14:49, 13 June 2023 (UTC)

June 13

Shears and goose

Found the phrase in a photo caption in a US President Andrew Johnson biography (cf photo added to William Andrew Johnson); gather from Google that this is the professional "symbol" of tailors. But what does "goose" describe here? Also interested in general phrase/word history/etymology. I tried OED and nothing came up TIA jengod (talk) 09:27, 13 June 2023 (UTC)

According to Wiktionary, a wikt:goose iron or "wikt:tailor's goose" is an old-fashioned pressing iron heated with coals. Fut.Perf. ☼ 10:17, 13 June 2023 (UTC)

• The "goose" seems to come from the fact that the curved handle was shaped like the neck of two geese. Also see our article on clothes iron. --Cookatoo.ergo.ZooM (talk) 14:39, 13 June 2023 (UTC)

OED says "A tailor's smoothing-iron. Plural gooses. [So called from the resemblance of the handle to the shape of a goose's neck.]" DuncanHill (talk) 14:46, 13 June 2023 (UTC)

And you can see a picture of Andrew Johnson's goose here, courtesy of the Andrew Johnson National Historic Site. DuncanHill (talk) 15:08, 13 June 2023 (UTC)

Bravo everyone and thanks. Will link to wikt. Much appreciated. jengod (talk) 16:13, 13 June 2023 (UTC)

Enumeration

1. Does Polish use letter Ł in enumeration?
2. Does Slovene use letters Č, Š, Ž in enumeration?
3. Does Icelandic use letters Þ, Æ, Ö in enumeration?
4. Does Spanish use letter Ñ in enumeration?
5. Does Estonian use letters Õ, Ä, Ö, Ü in enumeration?

--40bus (talk) 20:08, 13 June 2023 (UTC)

Re 1: No, letters with diacritics are not normally used for enumeration in Polish. — Kpalion^(talk) 21:43, 13 June 2023 (UTC)

Re 4: I am not aware of any Spanish numbers (be they cardinal or ordinal) which contain the n-with-tilde. Here's an article about Spanish numbers.[9] ←Baseball Bugs ^{What's up, Doc?} carrots→ 22:29, 13 June 2023 (UTC)

The query is probably about "counting" with letters, like Section A, B, C and so on... 惑乱 Wakuran (talk) 22:44, 13 June 2023 (UTC)

Aha. Supposing they even do that in Spanish, it seems unlikely they would use special characters, such as CH, LL, RR or Ñ. But it would be interesting to see a Spanish example of using letters "as numbers". ←Baseball Bugs ^{What's up, Doc?} carrots→ 23:04, 13 June 2023 (UTC)

Chinese occasionally enumerates 甲、乙、丙、丁... Not exactly Ordinal letters, but see Sexagenary cycle for further info. Folly Mox (talk) 23:25, 13 June 2023 (UTC)

Street sign in Mannheim

For what it's worth, in German I and J are traditionally regarded as equivalent for this purpose. For example, the city centre of Mannheim has a unique addressing system, where each block has a combination of a number and a letter (e.g. A1, C3, etc.). In this system, there is no I, but only a J, which is, however, pronounced not "Jot" (the German name for the Letter J) but "I". --Jbuchholz (talk) 08:32, 14 June 2023 (UTC)

In classical Fraktur fonts there was no distinction between the I and J majuscules,^[10] which means one could not use both in an enumeration (or, rather, an "elitteration".) Later Fraktur versions created an artificial and minimal distinction by making the tail of the I shorter and that of the J longer – ℑ versus 𝔍. I suppose the lack of an I in the Mannheim system goes back to this lack of distinction.  --Lambiam 11:29, 14 June 2023 (UTC)

Lambiam -- I and J weren't distinguished as separate letters (nor U and V) in the Latin alphabet generally before the 17th century. Even after the visual letter-forms J and V were specialized for consonantal use, and I and U for vowel use, the question of whether I and J were separate letters of the alphabet was sometimes still unclear or disputed. See this 1760 sampler where U and V are sometimes distinct, sometimes not, but I and J are not distinct... AnonMoos (talk) 18:05, 14 June 2023 (UTC)

True, but the indistinguishability of the majuscules in Fraktur persisted long after also in German typography the miniscules i and j came to be used like they are today. See for example here, where the I and J of "Im Junius" use the same grapheme, while the i and j of "mit jungem" are distinct.  --Lambiam 23:12, 14 June 2023 (UTC)

I looked at some Scrabble boards, which use letters to enumerate the column. Polish, Spanish and Estonian Scrabble boards do not use any of these letters for enumeration. Slovene puts the given letters at the end of the alphabet, so they are beyond the number of rows on a board, and I couldn't find a Scrabble board in Icelandic. If it's of any interest, the Scrabble derivative bcl:Dama Nin Tataramon uses the ng digraph for the column between N and O.  Card Zero  (talk) 20:12, 14 June 2023 (UTC)

While Polish doesn't use the letters Ą, Ć, Ę, Ł, Ń, Ó, Ś, Ź, Ż (or the digraphs Ch, Cz, Dz, Dź, Dż, Rz, Sz) in enumeration, it does use Q, V and X for that purpose, even though they aren't used in writing of any native Polish words. — Kpalion^(talk) 08:21, 15 June 2023 (UTC)

When the Gregorian calendar was constructed there were 30 lines of epacts (there still are), each identified by a letter. The series began in lower case, running from a to u, missing out j and o along the way. I wondered why they stopped at u, the nineteenth letter in this series (there are 19 golden numbers along the top), then spotted that the series went ...16, 17, 18, 29. But it continued 20, 21, 22..., so that '29' looks to be a misprint. Anyway, the remaining 11 letters were upper case A, B, C, D, E, F, G, H, M, N, P. [11]. Make of that what you will. 92.27.154.97 (talk) 09:39, 15 June 2023 (UTC)

Some apartment buildings in Poland use letters to name their entrances, and some of them (at least in Poznań) use letter Ł. In fact, all such buildings that have more than 12 entrances (those that go past L) use Ł. One building in Poznań use letter Ż and another there uses letter Ź (according to OpenStreetMap). None of the buildings use Q, V or X. And can you find any example of using special letters in enumeration in any language which has many special letters between basic Latin letters (like Slovene, Hungarian, Icelandic or Romanian)? Esperanto does not qualify. --40bus (talk) 14:39, 15 June 2023 (UTC)

What I wrote holds for Polish legal documents, that I'm sure of. I don't think I've ever seen "Polish letters" used in building numbering; I'd like to see an example. I tried to look at maps of residential areas in Poznań at Targeo, but could only find instances of entrance L followed immediately by entrance M, not Ł. — Kpalion^(talk) 07:39, 16 June 2023 (UTC)

More on this at Wikipedia:Reference desk/Archives/Language/2023 April 10#Questions. As for asking the same question over and over again (something the OP excels at) see Wikipedia:Reference desk/Archives/Language/2023 April 15#More questions and Wikipedia:Reference desk/Archives/Language/2023 April 22#Questions. 92.27.154.97 (talk) 09:05, 16 June 2023 (UTC)

June 14

LLM's and linguistic theory

Are linguistic theorists paying attention to stuff like ChatGPT? Are any new ideas coming out? For example, has the idea of universal grammar been affected? I see all kinds of nonsense coming out of ChatGPT, but it always seems to be grammatical, with the grammar rules apparently absorbed from the training text corpus somehow. Thanks. 2601:644:8500:C9F0:0:0:0:38B4 (talk) 08:22, 14 June 2023 (UTC)

Chomsky has been rather dismissive, stating that "the LLM systems are designed in such a way that they cannot tell us anything about language".^[12] While his arguments are rather solid, I am not wholly convinced that their relative success cannot serve a role in generating questions that deserve attention by linguists. Take the aspect of grammatical competence of language acquisition as learning to discern patterns. It raises an IMO important and interesting question about human cognition: Which kinds of patterns can be discovered, recognized and then be used generatively. (For example, consider the Thue–Morse sequence 01101001100101101001011001101001.... It is easy enough to recognize, but even if you understand it very well, it is hard to utter a large subsequence without making a mistake.) This may by itself be a fruitful question, but it also has a bearing on any theory of universal grammar, since a good theory must exclude grammars with unlearnable patterns. The first proposals formalizing TG admitted grammars for any recursive language and even non-recursive languages,^[13] which was clearly too lax.  --Lambiam 10:51, 14 June 2023 (UTC)

2601:644:8500:C9F0:0:0:0:38B4 -- From the point of view of linguists, AI chatbots (in their generative function) aren't all that much more than extremely fancy and sophisticated Markov chain devices. To really understand language, you need to have a mental model of the world -- and if a machine doesn't have a mental model of the world, then huge masses of language statistics can enable it to perform certain tasks within a certain semi-acceptable margin of error, but will not truly compensate for the lack of understanding. Many of these issues are explained in Douglas Hofstadter's 2018 analysis of Google Translate. One classic example is the following extremely brief dialogue -- Woman: "I'm leaving." Man: "Who is he?" It's just six words, but vast text databases probably won't help you too much in understanding who it is that the pronoun "he" refers to, if you don't have knowledge of the world... AnonMoos (talk) 11:19, 14 June 2023 (UTC)

For a somewhat different take, see the article "Emergent Abilities of Large Language Models".^[14] See also "Are Emergent Abilities of Large Language Models a Mirage?".^[15] I think the discussion is not yet closed; all make some strong points, but it is IMO impossible to see clearly where the rapid developments may take us.  --Lambiam 13:22, 14 June 2023 (UTC)

One thing is very clear -- if you aren't even trying to build a mental model of the world, then it's exponentially unlikely that you'll end up with a mental model of the world. Without this, to a significant degree all the program is doing is shuffling symbols around without meaningfully understanding such symbols. AnonMoos (talk) 18:09, 14 June 2023 (UTC)

It may be "exponentially unlikely", but LLMs nevertheless seem capable of simulating having a model of the world, in the sense that they exhibit behaviour that one would normally consider made possible only by internal inspection of a mental model. This includes LLMs appearing to have a theory of mind, or to have internalized maps of (parts of) the world representing spatial relationships. This was entirely unexpected, and how this is possible is not understood.  --Lambiam 22:48, 14 June 2023 (UTC)

"--L:

Instructions.

I wish you to imagine the eminent linguist professor Noam Chomsky having a public debate with a rather unknown researcher in the philosophy of linguistics, Dr. Chad Giuppetti. The debate is titled "Can linguistic theorists learn from Large Language Models?" and is is held in an auditorium before an audience of mainly linguistics and philosophy students. Chomsky defends the viewpoint that Large Language Models, being essentially "stochastic parrots" that merely imitate patterns found in human-produced text, cannot tell us anything about language. Giuppetti presents a different viewpoint, namely that explanations for observed unexpected and not yet quite understood abilities of Large Language Models may turn out to also have some explanatory power for the equally poorly understood linguistic competence of humans.

In the first round of the debate, the debaters start by each briefly stating their respective positions, whereupon each comments on the other's viewpoint. Each attempts to present their position as persuasively as they can. There is a moderator, who may intercede if any of the debaters commits an informal fallacy.

Present a record of the first round as you imagine it may unfold.

ChatGPT:

Moderator: Ladies and gentlemen, esteemed linguistics and philosophy students, welcome to tonight's debate titled "Can linguistic theorists learn from Large Language Models?" We have the honor of hosting two distinguished experts in the field: Professor Noam Chomsky, an eminent linguist, and Dr. Chad Giuppetti, a researcher in the philosophy of linguistics. Let's begin with the opening statements. Professor Chomsky, you may begin.

Chomsky: Thank you, moderator. Ladies and gentlemen, I stand before you today to argue that Large Language Models (LLMs) are nothing more than stochastic parrots, mere imitators of human-produced text. While they may possess impressive computational capabilities, they lack the understanding and insight that is fundamental to language. LLMs can mimic patterns found in human language, but they do not truly comprehend the underlying structure and meaning. Language is not merely a statistical game, and we must look beyond LLMs to unravel the mysteries of human linguistic competence.

Giuppetti: Thank you, Professor Chomsky, and to all of you present here. I appreciate the opportunity to engage in this debate. While I respect Professor Chomsky's groundbreaking contributions to linguistics, I propose a different perspective. LLMs have demonstrated remarkable abilities to generate coherent and contextually appropriate text, even in complex linguistic tasks. These abilities, although not fully understood, provide us with valuable insights into language phenomena that have eluded us for years. Exploring the explanations behind these abilities could potentially shed light on the equally enigmatic linguistic competence of humans.

Chomsky: I understand the allure of LLMs and their achievements, but we must not confuse their proficiency in statistical modeling with true linguistic understanding. LLMs lack intentionality, consciousness, and the capacity for genuine creativity that humans possess. Their success lies in the vast amount of data they consume and their ability to make probabilistic predictions. However, language is not reducible to probabilities alone. We need to focus on the underlying principles that guide human language acquisition and usage, rather than relying on the superficial imitations of LLMs.

Giuppetti: I agree that LLMs do not possess consciousness or intentionality, but we cannot ignore the fact that they excel at tasks that require some level of linguistic reasoning. Their success suggests that there might be computational principles at play, which could help us understand the building blocks of human language. By studying the unexpected abilities of LLMs, we may uncover hidden patterns and mechanisms that contribute to human linguistic competence. The analogy between LLMs and humans might not be perfect, but it can provide valuable insights into the nature of language.

Moderator: Thank you both for your insightful opening statements. Before we proceed, I would like to remind our debaters to maintain a respectful and rigorous discourse. Please refrain from any informal fallacies in your arguments. Let's continue with the second round, where each of you will have the opportunity to delve deeper into your positions and respond to one another's arguments.

--L:

OK. Now, actually, after the first round the audience has an opportunity to submit questions during a brief intermission, which the moderator will then use as a basis for the continuation of the debate. What could be five interesting questions submitted by members of the audience?

ChatGPT:

Certainly! Here are five interesting questions that members of the audience may have submitted during the intermission:

1. Question for Professor Chomsky: You argue that Large Language Models (LLMs) lack genuine linguistic understanding. Could you elaborate on what specific aspects or features of language you believe LLMs fail to capture? And how do these aspects contribute to human linguistic competence?
2. Question for Dr. Giuppetti: While LLMs demonstrate impressive computational abilities, how do we ensure that the patterns and mechanisms they reveal are truly applicable to human language? What potential risks or limitations should we consider when drawing conclusions from LLMs about human linguistic competence?
3. Question for Professor Chomsky: LLMs have been successful in tasks such as translation and summarization, where they seem to exhibit a level of linguistic reasoning. How would you explain their ability to perform these tasks if they lack genuine linguistic understanding? Are there alternative explanations for their proficiency?
4. Question for Dr. Giuppetti: Can you provide examples of specific linguistic phenomena or abilities that LLMs have showcased but remain poorly understood in terms of human language? How can studying LLMs help us gain insight into these particular aspects of language?
5. Question for both debaters: Considering the ongoing advancements in LLM technology, what potential ethical implications do you foresee in terms of the impact on human linguistic competence, language preservation, and cultural diversity? How should we navigate these challenges while embracing the potential benefits of LLM research?

These questions touch upon various aspects of the debate, from the nature of linguistic understanding and the applicability of LLMs to human language, to the risks, limitations, and ethical considerations surrounding LLM research. They would provide an engaging basis for the continuation of the debate."

 --Lambiam 17:21, 14 June 2023 (UTC)

Thanks all. Here is an interesting article indicating that LLM's really do (maybe) make world models. Summary: by showing an LLM the move lists of a bunch of Othello games, the LLM is able to figure out the rules of the game and model the game board state. Also, Transformers (the mechanism inside the LLM) are much more complicated and stateful than Markov chains are. That article helped convince me that LLM's are demonstrating actual intelligence for some reasonable definition of intelligence. Not very high intelligence perhaps, but getting there. 2601:644:8500:C9F0:0:0:0:38B4 (talk) 20:02, 15 June 2023 (UTC)

June 15

Becoming

This sentence caught my eye in a Today report:

He spoke with Jenna as Rishi Sunak became Britain's third prime minister in seven weeks on Oct. 25 amid a cycle of political and economic chaos in the United Kingdom.

Isn't the syntax wrong? I would have thought it meant that three people entered the office of Prime Minister in the space of 49 days. 89.243.8.4 (talk) 16:03, 15 June 2023 (UTC)

It seems clear to me. The three people are Johnson, Truss and Sunak. Because of Truss's short occupancy of the role there's a seven week span which has three different prime ministers. It does not mean all three started in the job during that seven weeks, just that they occupied the role. Only Sunak is mentioned as entering, i.e. becoming, PM. 92.41.105.60 (talk) 16:20, 15 June 2023 (UTC)

I agree with 92: it's normal. It doesn't say he was the third to become PM in seven weeks (which would have meant what you said) but that he became the third PM in seven weeks. ColinFine (talk) 16:52, 15 June 2023 (UTC)

See also Year of three prime ministers. Alansplodge (talk) 17:11, 15 June 2023 (UTC)

Also Year of four popes and Year of the Five Emperors. --142.112.221.43 (talk) 17:37, 15 June 2023 (UTC)

It happens often enough in Vaticanology that year of three popes is a name given to it. It only takes one pope entering and leaving the post in the same year. Year of 4 popes on the other hand seems to have only happened once. 2601:644:8500:C9F0:0:0:0:38B4 (talk) 20:07, 15 June 2023 (UTC)

References

Possessive form of "mathematics"

Is it "mathematics' " or "mathematics's"? — Preceding unsigned comment added by 134.242.92.97 (talk) 17:06, 15 June 2023 (UTC)

Nouns plural in form, singular in meaning, add only an apostrophe: [e.g.] mathematics' rules... [16] Alansplodge (talk) 17:15, 15 June 2023 (UTC)

That's just one style guide. It also says that "Singular proper nouns ending in s, add only an apostrophe", whereas both the plain apostrophe and the apostrophe-s are accepted (James' or James's). And for "singular common nouns ending in s" it says that the choice depends on the following word, a guideline I've never even heard of before. In this case, I suggest the best choice is to just write "math's"! (At least unless you're British and spell the base form "maths"...) --142.112.221.43 (talk) 17:43, 15 June 2023 (UTC)

Yes, which English are you writing in? For example if Canadian English, Canadian Press (can't provide link, is subscription site, but you can look up the book equivalent The Canadian Press Stylebook) says the following:

• 2. Plural nouns ending in s take an apostrophe alone. teachers’ apples, the two peoples’ history, the Joneses’ daughter
• 3. Singular nouns and names ending in s (or an s sound) normally take an ’s. Chris’s sandwich, the witness’s testimony
• 9. In general, inanimate objects take an of phrase rather than an apostrophe. the colour of the coat, not the coat’s colour, the incidence of flu, not the flu’s incidence 70.67.193.176 (talk) 19:14, 15 June 2023 (UTC)

Stress of words ending in -ative

Do many people give nonstandard stress to many words ending in -ative?? (I can find only one Wiktionary entry, wikt:demonstrative, that reveals a word where this is true.) Georgia guy (talk) 17:57, 15 June 2023 (UTC)

What would be the standard stress? ←Baseball Bugs ^{What's up, Doc?} carrots→ 02:10, 16 June 2023 (UTC)

We say dem'onstrate but de.mon'strative. I haven't heard dem'onstrative. Doug butler (talk) 02:54, 16 June 2023 (UTC)

So would stressing the DEM part of "demonstrative" theoretically be "standard"? ←Baseball Bugs ^{What's up, Doc?} carrots→ 03:41, 16 June 2023 (UTC)

JFYI, IPA stress marks are placed before the stressed syllable. Nardog (talk) 05:27, 16 June 2023 (UTC)

Thanks (sheepish grin) shoulda stuck to caps. Doug butler (talk) 06:37, 16 June 2023 (UTC)

Derogative is similar (contrasted with derogate). Wiktionary doesn't give a pronunciation. Webster's in 1913, second link here, puts the stress on the rog. The Free Dictionary has a robotic voice which puts the stress everywhere else instead, contradicting the Collaborative International Dictionary of English pronunciation guide on the same page (which is itself derived from Webster's 1913).  Card Zero  (talk) 09:01, 16 June 2023 (UTC)

June 16

Chinese names

Mao Tse-tung has been re-rendered Mao Zedong with recent schemes of romanising Chinese. Why hasn't Sun Yat-sen been re-rendered to avoid the hyphen? Nyttend (talk) 00:30, 16 June 2023 (UTC)

Re-rendered by whom? The 'recent scheme' was designed by Chinese philologists (in the 1950s) primarily for the use of Chinese (actually Modern Standard Mandarin) speakers/writers, unlike previous schemes such as Yale and Wade–Giles that were designed by Western philologists for Western readers. This has led to many Western misconceptions, because the pronunciations of letters in Pinyin is often not, and is not intended to be, those usual in Western orthographies – instead they have been repurposed for MSM, which has sounds that English (for example) does not have or does not recognise.

An example is 'Beijing', the 'new' spelling in Pinyin, in which 'B' and 'j' are not pronounced as they are in English – 'B' is an unaspirated 'p' (such as in 'spark' rather than 'pit') and 'j' is nonexistent in English but could be rendered something like 'chy' or 'kw'.

So to see a deliberate Pinyin rendering of Sun Yat-sen, one would have to be reading either a MSM Pinyin reference to him, or a Western-language reference whose writer has chosen to use the Pinyin rendering.

What is the Pinyin rendering of Sun Yat-sen, anyway? {the poster formerly known as 87.81.230.195} 46.65.228.117 (talk) 04:23, 16 June 2023 (UTC)

46.65.228.117 -- If some Chinese sounds are not directly comparable to English sounds, then it's inevitable that any rendering of Chinese into the Latin alphabet will be misleading to those English speakers without knowledge of Chinese. That's the nature of Romanization. The Wade-Giles system used apostrophes and diacritic marks which were most often simply ignored in general English-language newspapers, further obscuring things. At least Pinyin makes only a very limited use of diacritics. You can see a large number of transcriptions of Sun Yat-sen's name on his Wikipedia article. The conventional Romanization of Sun Yat-sen's name in English hasn't been updated because his life is not viewed as a PRC-relevant topic among English speakers, presumably... AnonMoos (talk) 05:08, 16 June 2023 (UTC)

I agree, and I'm not complaining about Pinyin being misleading to English speakers at first glance – it wasn't primarily intended for them in the first place. I'm complaining about lazy Western jounalists (who are supposed to do research) failing to grasp how Pinyin works and themselves misleading the public by pronouncing Pinyin letters with inappropriate English sounds. Incidentally, I am English myself, and have completely forgotten what Cantonese I learned as a small child in Hong Kong.

Pinyin would be Sun Yixian. "Sun Yat-sen", like "Chiang Kai-shek" (Pinyin: Jiang Jieshi) is not romanised Mandarin, but romanised Cantonese. —Kusma (talk) 07:51, 16 June 2023 (UTC)

So OP Nyttend is asking why "Sun Yat-sen" is not rendered as "Sun Yixian". In Pinyin-written MSM it doubtless is; in Western media this would not be recognised, and is not used, for example, as the title of his en-Wikipedia's article (though it redirects to it) because of WP:COMMONNAME. {The poster formerly known as 87.81.230.195} 46.65.228.117 (talk) 09:46, 16 June 2023 (UTC)