4th tone – 3rd tone, it would appear:
Well, maybe not; the diacritics are probably meant to indicate vowel quality, but I don’t know what system (if any) they are using.
Ben Zimmer writes:
The diacritics may be intended to evoke pinyin tone marks, but they’re also reminiscent of dictionary-style phonetic respelling and stress marking. The grave accent on “ì” could be intended as an indicator of primary stress, though that’s more typically marked with an acute accent. And the breve on the “ĭ” is a common enough way to represent /ɪ/ (the macron is used for long vowels and the breve for short vowels — see, e.g., Phonics on the Web). But this use of diacritics as typographical ornamentation is never very consistent — recall the styling of the play Chinglish as “Ch’ing·lish”.
The illustration appears at the top of this article:
- Kou Jie, “China to standardize use of English on public signs“, People’s Daily Online (6/21/17)
It turns out that the image used by the People’s Daily originally appeared as a promotion for the play Chinglish that Ben mentioned, specifically for its performance by the Singaporean theater company Pangdemonium in 2015. See the Pangdemonium website, as well as local coverage by PopSpoken and Today. So the People’s Daily may have searched for a “Chinglish” image online and borrowed this one, without giving proper credit. (Credit should go to Olivier Henry of MILK Photographie.)
The six individuals in the picture seem to be aspiring to some idealized form of Chinglish in the sky above, overlying the cloud shrouded five star design of the Chinese flag, leading them on. The thrust of the People’s Daily article, however, is anything but adulatory of Chinglish:
Chinese authorities on June 20 issued a national standard for the use of English in the public domain, eradicating poor translations that damage the country’s image.
The standard, jointly issued by China’s Standardization Administration and General Administration of Quality Supervision, Inspection and Quarantine, aims to improve the quality of English translations in 13 public arenas, including transportation, entertainment, medicine and financial services. It will take effect on Dec. 1, 2017.
According to the standard, English translations should prioritize correct grammar and a proper register, while rare expressions and vocabulary words should be avoided. The standard requires that English not be overused in public sectors, and that translations not contain content that damages the images of China or other countries. Discriminatory and hurtful words have also been banned. The standard provided sample translations for reference, and warned against direct translation.
There are perpetual plans for eliminating Chinglish in China, but they are unlikely ever to materialize unless professional translators are sought after for their expertise and paid accordingly.
Earlier calls for the elimination of English more generally are no longer heard from responsible persons:
- “English Banned in Chinese Writing ” (12/23/10)
Now the goal is more reasonably just to get rid of Chinglish, but that will not happen on December 1, 2017 when the new standards go into effect. Although it will take many years for their full implementation and realization, the standards are admirable goals to aim for.
- Neil Connor, “Beijing wages war on ‘Chinglish’ to prevent translation gaffes“, The Telegraph (6/23/17)
[h.t. Jim Fanell, Toni Tan]
LIFE magazine March 14, 1955 fashion feature: MIAMI MOVES UP IN STYLE—Breezy clothes for warm weather come from a likely source. “Newest of the Florida booms is in the field of fashion. With its fashion industry grown 10 times in size since 1945, Miami now has 125 firms manufacturing women’s apparel, last year sold $55 million worth of clothes for warm weather at any season of the year.”
Query from a reader:
Is it correct to use the word assuage to indicate a lessening of something? That is, it is often used in the realm of feelings, i.e. assuage hunger, assuage grief, etc. But would it be acceptable to use to indicate the lessening of something more tangible, such as assuage criminality, assuage the flow of water, assuage drug use.
I probably wouldn’t use assuage to describe the lowering of flood waters or the amelioration of traffic jams. But I don’t have any special standing to rule on such matters, so as usual, let’s look at how others use the word.
The OED’s entry for assuage, which is flagged as “not yet … fully updated (first published 1885)”, has several senses marked as “arch. or Obs.” that don’t involve “angry or excited feelings”, or beings in such a state.
There’s the transitive form glossed “To abate, lessen, diminish (esp. anything swollen)”, with examples like
1774 J. Bryant New Syst. II. 284 The Dove..brought the first tidings that the waters of the deep were asswaged.
There’s the intransitive inchoative version of the same, glossed “To grow less, diminish, decrease, fall off, die away; to abate, subside”, with examples like
1611 Bible (King James) Gen. viii. 1 And the waters asswaged .
COCA has 509 instances of “assuage”, 134 of “assuaged”, 46 of “assuaging”, and 17 of “assuages”. Looking at a random sample of 100, we find that all 100 are transitive, and that in 98 of them, what’s assuaged is an negatively-evaluated emotion or feeling or concern (“the community’s grief”, “his guilt”, “such mortal concerns”, “the twitchy sensation in my cells”, “white opposition to slave conversion”, “my hunger”, “Democratic anxieties”, “India’s complaints”, “feelings of humiliation”, the monarch’s fears”, “his own damaged pride”, “the egos of movie stars”, “my curiosity”, …), or an person or group of people subject to such emotions or feelings or concerns (“his uneasy party”, “the academic intellectual community”, “the larger man”, “international critics of the war”, “his jittery passenger”, “the chiefs”, “the dealers”, …).
The two exceptions in the sample are these:
In The Efficiency Trap, Steve Hallett claims that we will exhaust many of our resources by the 2030s, and violence and chaos will erupt as a result. Hallett proposes recycling and growing food locally as possible means of assuaging the damage.
The measure, which awaits Senate approval of a minor amendment next week, can not assuage the impending disaster that will kill virtually all the fish in the Dolores River this summer.
With respect to the specific examples in the query, Google finds
“assuage criminality”: one example [link] Please reconsider your gig – don’t play for a segregated audience in Israel and make of yourself a balm to assuage criminality.
“assuage the flow of water”: no examples (though see biblical examples cited by the OED)
assuage drug use: one example [link] Becker’s neoliberal drug policy presumes to assuage drug use and addiction by the instantiation of a highly regulated market as a system of control.
So the verdict of norma loquendi seems to be that applying assuage to things other than people and their feelings is out of fashion and currently marginal.
My own investigations on the Bronze Age and Early Iron Age peoples of Eastern Central Asia (ECA) began essentially as a genetics cum linguistics project back in the early 90s. That was not long after the extraction of mtDNA (mitochondrial DNA) from ancient human tissues and its amplification by means of PCR (polymerase chain reaction) became possible.
By the mid-90s I had grown somewhat disenchanted with ancient DNA (aDNA) studies because the data were insufficient to determine the origins and affiliations of various early groups with satisfactory precision, neither spatially nor temporally. Around the same time, I began to realize that other types of materials, such as textiles and metals, provided powerful diagnostic evidence.
By the late 90s, combining findings from all of these fields and others, I was willing to advance the hypothesis that some of the mummies of ECA, especially the earliest ones dating to around 1800 BC, may have spoken a pre-proto-form of Tocharian when they were alive (some people think it’s funny or scary to imagine that mummies once could speak). This hypothesis was presented at an international conference held at the University of Pennsylvania in April, 1996, which was attended by more than a hundred archeologists, linguists, geneticists, physical anthropologists, textile specialists, metallurgists, geographers, climatologists, historians, mythologists, and ethnologists — including more than half a dozen of the world’s most distinguished Tocharianists. It was most decidedly a multidisciplinary conference before it became fashionable to call academic endeavors by such terms (see ” Xdisciplinary” [6/14/17]). The papers from the conference were collected in this publication:
Victor H. Mair, The Bronze Age and Early Iron Age Peoples of Eastern Central Asia (Washington, D.C.: Institute for the Study of Man Inc. in collaboration with the University of Pennsylvania Museum Publications, 1998). 2 vols.
“Early Indo-Europeans in Xinjiang” (11/19/08)
It is only very recently, within the last ten years or so, that Y-chromosome analysis has been brought into play for the study of ancient DNA. See Toomas Kivisild, “The study of human Y chromosome variation through ancient DNA“, Human Genetics, 2017; 136(5): 529–546; published online 2017 Mar 4. doi: 10.1007/s00439-017-1773-z.* Since only males carry the Y-chromosome, this has made it possible to trace the patriline of individuals. This, coupled with the massive accumulation and detailed analysis of modern DNA with increasing sophistication and the rise of the interdisciplinary (!) field referred to as genomics, has made studies on the genetics of premodern people, including their origins, migrations, and affinities, far more exacting than it was during the 90s when I did the bulk of my investigations on the early inhabitants of the Tarim Basin.
Now it is possible to draw on the results of genetics research to frame and more reliably solve questions about the development of languages from their homeland to the far-flung places where they subsequently came to be spoken. One such inquiry is described in this article:
Tony Joseph, “How genetics is settling the Aryan migration debate“, The Hindu (6/16/17).
It is significant that this substantial article appeared in The Hindu, since there is a strong bias against such conclusions among Indian nationalists (see “Indigenous Aryans“). It begins thus:
New DNA evidence is solving the most fought-over question in Indian history. And you will be surprised at how sure-footed the answer is, writes Tony Joseph
The thorniest, most fought-over question in Indian history is slowly but surely getting answered: did Indo-European language speakers, who called themselves Aryans, stream into India sometime around 2,000 BC – 1,500 BC when the Indus Valley civilisation came to an end, bringing with them Sanskrit and a distinctive set of cultural practices? Genetic research based on an avalanche of new DNA evidence is making scientists around the world converge on an unambiguous answer: yes, they did.
Joseph’s paper is informed, sensitive, balanced, and nuanced. This is responsible science journalism.
The scientific paper itself, “A Genetic Chronology for the Indian Subcontinent Points to Heavily Sex-biased Dispersals” by Marina Silva, Marisa Oliveira, Daniel Vieira, Andreia Brandão, Teresa Rito, Joana B. Pereira, Ross M. Fraser, Bob Hudson, Francesca Gandini, Ceiridwen Edwards, Maria Pala, John Koch, James F. Wilson, Luísa Pereira, Martin B. Richards, and Pedro Soares, was published in BMC Evolutionary Biology (3/23/17) ( DOI: 10.1186/s12862-017-0936-9).
I’m skeptical of many of the claims put forward by geneticists concerning origins and dispersals, not just about humans, but also about horses, dogs, cats, plants, and so forth. This study, however, is both cautious and solid. Moreover, it fits well with the archeological evidence (more below).
Here are two key paragraphs from the scientific paper (numbers in square brackets are to accessible references):
Although some have argued for co-dispersal of the Indo-Aryan languages with the earliest Neolithic from the Fertile Crescent [88, 89], others have argued that, if any language family dispersed with the Neolithic into South Asia, it was more likely to have been the Dravidian family now spoken across much of central and southern India . Moreover, despite a largely imported suite of Near Eastern domesticates, there was also an indigenous component at Mehrgarh, including zebu cattle [85, 86, 90]. The more widely accepted “Steppe hypothesis” [91, 92] for the origins of Indo-European has recently received powerful support from aDNA evidence. Genome-wide, Y-chromosome and mtDNA analyses all suggest Late Neolithic dispersals into Europe, potentially originating amongst Indo-European-speaking Yamnaya pastoralists that arose in the Pontic-Caspian Steppe by ~5 ka, with expansions east and later south into Central Asia in the Bronze Age [53, 76, 93, 94, 95]. Given the difficulties with deriving the European Corded Ware directly from the Yamnaya , a plausible alternative (yet to be directly tested with genetic evidence) is an earlier Steppe origin amongst Copper Age Khavlyn, Srednij Stog and Skelya pastoralists, ~7-5.5 ka, with an infiltration of southeast European Chalcolithic Tripolye communities ~6.4 ka, giving rise to both the Corded Ware and Yamnaya when it broke up ~5.4 ka .
An influx of such migrants into South Asia would likely have contributed to the CHG component in the GW [VHM: genome-wide] analysis found across the Subcontinent, as this is seen at a high rate amongst samples from the putative Yamnaya source pool and descendant Central Asian Bronze Age groups. Archaeological evidence suggests that Middle Bronze Age Andronovo descendants of the Early Bronze Age horse-based, pastoralist and chariot-using Sintashta culture, located in the grasslands and river valleys to the east of the Southern Ural Mountains and likely speaking a proto-Indo-Iranian language, probably expanded east and south into Central Asia by ~3.8 ka. Andronovo groups, and potentially Sintashta groups before them, are thought to have infiltrated and dominated the soma-using Bactrian Margiana Archaeological Complex (BMAC) in Turkmenistan/northern Afghanistan by 3.5 ka and possibly as early as 4 ka. The BMAC came into contact with the Indus Valley civilisation in Baluchistan from ~4 ka onwards, around the beginning of the Indus Valley decline, with pastoralist dominated groups dispersing further into South Asia by ~3.5 ka, as well as westwards across northern Iran into Syria (which came under the sway of the Indo-Iranian-speaking Mitanni) and Anatolia [12, 95, 97, 98].
The spread of R1a into South Asia had earlier been securely documented in Peter A. Underhill, et al., “The phylogenetic and geographic structure of Y-chromosome haplogroup R1a“, European Journal of Human Genetics (2015) 23, 124–131; doi:10.1038/ejhg.2014.50; published online 26 March 2014.
The precise coalescence of R1a within South Asia was identified in Monika Karmin, et al., “A recent bottleneck of Y chromosome diversity coincides with a global change in culture“, Genome Research (2015);
This kind of male migration theory is proposed with arguments based on archeological evidence in the last pages of H.-P. Francfort, “La civilisation de l’Oxus et les Indo-Iraniens et Indo-Aryens”, in: Aryas, Aryens et Iraniens en Asie Centrale (Collège de France. Publications de l’Institut de Civilisation Indienne, vol. 72), G. Fussman, J. Kellens, H.-P. Francfort, et X. Tremblay (eds.) (Paris: Diffusion de Boccard, 2005) pp. 253-328. The complete paper is on academia website.
Michael Witzel has favored this, the (Indo-)Aryan Migration view, on linguistic and textual grounds since at least 1995 and was constantly criticized for saying so. See his papers of 1995, 2001:
“Early Indian History: Linguistic and Textual Parameters.” In: Language, Material Culture and Ethnicity: The Indo-Aryans of Ancient South Asia. Ed. G. Erdosy (Berlin/New York: de Gruyter 1995), 85-125; — Rgvedic history: poets, chieftains and politics, loc. cit. 307-352 combined pdf (uncorrected).
and the substrate paper of 1999:
“Early Sources for South Asian Substrate Languages.” Mother Tongue (1999, extra number) pdf
Some relevant Language Log posts:
“Dating Indo-European” (12/10/03)
“More on IE wheels and horses ” (1/10/09)
“Irish DNA and Indo-European origins” (12/31/15)
*For those who are interested in the development of aDNA Y-chromosome studies beginning in the 2000s, I have some additional documentation and several relevant papers that I can send to you.
[Thanks to Richard Villems, Toomas Kivisild, and Peter Underhill]
.. or at least six weeks of it, will be spent at the 2017 Jelinek Summer Workshop on Speech and Language Technology (JSALT) at CMU in Pittsburgh. As the link explains, this
… is a continuation of the Johns Hopkins University CLSP summer workshop series from 1995-2016. It consists of a two-week summer school, followed by a six-week workshop. Notable researchers and students come together to collaborate on selected research topics. The Workshop is named after the late Fred Jelinek, its former director and head of the Center for Speech and Language Processing.
I took part in the first of these annual summer workshops, back in 1995, as a member of the team focused on “Language Modeling for Conversational Speech Recognition“.
This summer, I’ll be part of a group whose theme is described as “Enhancement and Analysis of Conversational Speech“.
One of the group’s goals is to do a better job of “diarization”, i.e. keeping track of who spoke when in conversations. Existing systems do an especially bad job with overlapping speech, which can be extremely common.
Here’s a graphical representation of (accurate) diarization in a (real) conversation between Red and Blue:
And the same thing continued for a while (though not to the end of the conversation):
As discussed here, turn-taking overlaps are often cooperative rather than competitive — and it would be good to be able to supplement robust diarization with a functional analysis of conversational flow.
As the workshop progresses, I’ll post some updates.
This strikes me as an unusual obituary: Margalit Fox, “Paul Zukofsky, Prodigy Who Became, Uneasily, a Virtuoso Violinist, Dies at 73“, NYT 6/20/2017. It massively violates the precept de mortuis nil nisi bonum, describing its subject at great length as an “automaton” who was “deeply ill at ease with world”; an “arch-bridge troll”, full of “unbridled hubris”, “disdain for those less gifted than he”, and “an ample sense of self-worth”; “swift to run to judgment”, “meanspirited, sarcastic, rather bitter”; someone who would “look at [his audience] with utter contempt”, and on and on.
Margalit Fox certainly found plenty of sources for these judgments. But this litany of bitter score-settling is completely at odds with my own experience of Paul Zukofsky.
I first met Paul around 1976, when I was employed at Bell Labs in Murray Hill NJ, and he was the music director of the Colonial Symphony in Madison, a few miles west. He was planning to present Bach’s Fourth Brandenburg Concerto, and he needed a continuo player. I owned a harpsichord, had once taken a conservatory course in figured bass realization, and occasionally performed with professional and semi-professional chamber groups in the area, so Joan Miller recommended me to him.
Paul was then teaching at Stony Brook, so I treked out there to audition. That was an amazing experience — while I played the continuo part, Paul, with an occasional glance at the score, played the parts of all three soloists and the rest of the orchestra all at once on the violin. It was amazing. I had never seen anything like it. I managed keep my jaw off the floor, and made my way through the audition well enough to get the part.
This situation was inherently intimidating, and my own musical gifts were far below Paul’s. But he was charming and friendly, interested in talking about Bach’s music, and about music theory and the psychology of music, and he left me with a positive feeling about the whole experience.
For a while around that time, Paul became a regular visitor at Bell Labs, where he contributed to some interesting work, including these publications:
Ronald Knoll, Saul Sternberg, and Paul Zukofsky, “Subdivision of the beat: Estimation and production of time ratio by skilled musicians“, JASA 1976.
Mark Liberman, Joseph Olive, and Paul Zukofsky, “Studies of metric patterns“, JASA 1977.
Saul Sternberg, Ronald Knoll, and Paul Zukofsky, “Timing by Skilled Musicians“, in Diana Deutsch, Ed., Psychology of Music, 1982.
Throughout those interactions, I never met the cold, mean, unpleasant man depicted in the NYT obituary. On the contrary, Paul was always smart, engaged, friendly, and even convivial.
Maybe I have a thicker skin than the people who supplied Margalit Fox with so much bile. Or maybe Paul was different in later life than he was when I knew him.
But looking over the obituary, I see two other factors that might be relevant. One is Paul’s role as executor of his father’s estate — that’s a side of him that I never saw, and one that would not have been relevant before Louis Zukofsky died in 1978, which was after most of my interactions with Paul.
And the other factor might be his apparent reluctance to take up the standard role of a violin virtuoso, or at least to limit himself to playing that part. Perhaps he saw me and others at Bell Labs as part of his self-liberation from that role, rather than as part of the world that he needed to escape, and perhaps he therefore interacted differently with us.
Still, I have a feeling that most people could be unlucky enough to be treated to an obituary like the one under discussion. The recipe is clear: find people with a grudge, people on the other side of arguments, people who were offended on purpose or by accident, people who were disappointed, people with relevant prejudices, and select your quotes to play up the negatives and minimize the positives. The Paul Zukofsky I knew deserves better.
Update — a letter sent by Saul Sternberg to the New York Times:
I believe that this obituary gives a false impression of Zukofsky’s personality. The only indication that he could be a sweet, loving, caring person is the one quote (Kalish) “to those who understood him deeply…” If you look at the comments on slippedisc.com/2017/06/death-of-an-
It is as if, rather than providing a balanced description, the writer emphasized those aspects of his personality that would fit with her beliefs about his early life and her claims about his “emotional development” having been “sacrificed to professional prowess”.
I’ve known Paul Zukofsky for the past forty years, and although the names of many people have come up in our conversations and correspondence, I’ve seen no evidence of “his disdain for people less gifted than he”.
Also, the obit fails to mention the existence of the Zukofsky Quartet, named in his honor.
Update #2 — from Joshua Gordon:
It was good to read your commentary on the NYBTimes obituary for Paul Zukofsky, and I am sympathetic to your experience with him (he was an important mentor to me at Juilliard and beyond). I posted a new Facebook page for anybody who wants to share thoughts or materials on him called “In Memory of Paul Zukofsky“, I hope you’ll want to contribute to it.
When the parents are psycholinguists, the children get exposed to some weird stuff.
For example, the Stroop effect (words interfere with naming colors, e.g. GREEN RED BLUE) makes a great 4th grade science project; 9 year olds think it’s hilarious. There are lots of fun versions of the task (e.g., SKY FROG APPLE) but prudence dictates avoiding this variant in which taboo words like FUCK COCK PUSSY produced greater interference than neutral words like FLEW COST PASTA (p < .01).
Or, the kid knows that “I see that the clothes on the floor in your room have risen a couple of feet above sea level” means “clean up the mess, please” but also that this is an indirect speech act because the form of the utterance (an assertion) differs from its communicative intent (a request). Thus enabling exchanges such as “Can you take out the garbage???” “Is that an indirect speech act?”
I confess that we have actually had dinner conversations about the Transposed Letter Effect, the finding that with brief exposure, subjects frequently misperceive a stimulus such as ODRER as ORDER. It happens in real life, as in the sign on the left and the company logo (French Connection UK) on the right.
The explanation for the effect is interesting–well, I thought it was–having to do with statistical properties of English orthography and the fact that ODRER is closer to ORDER than to any other word. There’s a simple demo of the phenomenon here, if you’re interested.
For birthdays and other events greeting cards with terrible wordplay are just low hanging fruit. A recent Father’s Day card connected to my interest in accent and dialect:
I’m told that this is an old joke, popular in summer camp several years ago. Still, it does manage to alert a person to how much American regional accents can differ. On this occasion I psycholinguisplained that it also illustrates the folly of trying to reform English spelling to make the correspondences between spellings and pronunciations consistent, as in Finnish and most other alphabetic writing systems: there would need to be different spellings for each regional pronunciation of even simple words like NICE.
On the inside the card said I was “Rat nas”. Which is what you call kids who participate in dinner conversations about speech acts and spelling reform.
Adrienne LaFrance, “What an AI’s Non-Human Language Actually Looks Like“, The Atlantic 6/20/2017:
Something unexpected happened recently at the Facebook Artificial Intelligence Research lab. Researchers who had been training bots to negotiate with one another realized that the bots, left to their own devices, started communicating in a non-human language. […]
What does this language actually look like? Here’s an example of one of the bot negotiations that Facebook observed:
Bob: i can i i everything else . . . . . . . . . . . . . .
Alice: balls have zero to me to me to me to me to me to me to me to me to
Bob: you i everything else . . . . . . . . . . . . . .
Alice: balls have a ball to me to me to me to me to me to me to me
Bob: i i can i i i everything else . . . . . . . . . . . . . .
Alice: balls have a ball to me to me to me to me to me to me to me
Bob: i . . . . . . . . . . . . . . . . . . .
Alice: balls have zero to me to me to me to me to me to me to me to me to
Bob: you i i i i i everything else . . . . . . . . . . . . . .
Alice: balls have 0 to me to me to me to me to me to me to me to me to
Bob: you i i i everything else . . . . . . . . . . . . . .
Alice: balls have zero to me to me to me to me to me to me to me to me to
Not only does this appear to be nonsense, but the bots don’t really seem to be getting anywhere in the negotiation. Alice isn’t budging from her original position, anyway. The weird thing is, Facebook’s data shows that conversations like this sometimes still led to successful negotiations between the bots in the end, a spokesperson from the AI lab told me. (In other cases, researchers adjusted their model and the bots would develop bad strategies for negotiating—even if their conversation remained interpretable by human standards.)
This is strikingly reminiscent of Google Translate’s responses to certain sorts of nonsensical inputs — and for good reasons. See
“What a tangled web they weave“, 4/15/2017
“A long short-term memory of Gertrude Stein“, 4/16/2017
“Electric sheep“, 4/18/2017
“The sphere of the sphere is the sphere of the sphere“, 4/22/2017
“I have gone into my own way“, 4/27/2017
“Your gigantic crocodile!“, 4/28/2017
“More deep translation arcana“, 4/30/2017
The article’s author wrote to me this morning to ask some sensible questions, to which I tried to give sensible answers, most of which are quoted — you should read the whole thing. But if you’re in a hurry, here are her questions and my answers:
1. Does that truly count as language?
We have to start by admitting that it’s not up to linguists to decide how the word “language” can be used, though linguists certainly have opinions and arguments about the nature of human languages, and the boundaries of that natural class.
So let’s divide your question in two:
1a. Is it reasonable to use the ordinary-language word “language” to describe the system that the Facebook chatbots apparently evolved?
Answer: Apparently so. After all, we use that word to describe the ones and zeros of “machine language”, which is usually generated by compilers and assemblers for controlling digital hardware, without any humans involved in the process. Though my prediction would be that the Facebook chatbot’s communication process is pretty ephemeral, in the sense that it’s a sort of PR stunt built on an experimental accident, and in a few years it won’t exist even in the sense of having descendants connected by a direct evolutionary chain.
1b. Is the Facebook chatbot’s evolved version of English (“Facebotlish”?) like a new kind of human language, say a future version of English?
Answer: Probably not, though there’s not enough information available to tell. In the first place, it’s entirely text-based, while human languages are all basically spoken (or gestured), with text being an artificial overlay. And beyond that, it’s unclear that this process yields a system with the kind of word, phrase, and sentence structures characteristic of human languages.
2. Will machines eventually change the definition of “language” as we know it?
Well, there’s already the well-establish concept of “computer language”, which merits a new word sense — e.g. the OED’s sense 1.d. “Computing. Any of numerous systems of precisely defined symbols and rules devised for writing programs or representing instructions and data that can be processed and executed by a computer.” And note that some of these systems are specifically devised to be written by computer programs and not by people.
3. Have they already?
In the above sense, yes.
But you should keep in mind that the Facebook chatbots, whatever their performance in specified tasks, are almost certainly not “intelligent” in the general sense, or even the leading edge of a durable approach to digital problem-solving. See e.g. here or here…
The “expert systems” style of AI programs of the 1970s are at best a historical curiosity now, like the clockwork automata of the 17th century. We can be pretty sure that in a few decades, today’s machine-learning AI will seem equally quaint.
It’s easy to set up artificial worlds full of algorithmic entities with communications procedures that evolve through a combination of random drift, social convergence, and optimizing selection — just as it’s easy to build a clockwork figurine that plays the clavier.
Are those Facebook chatbots an example of this? Apparently.
Could it be true that at some point digital self-organizing systems will become capable enough to develop their own inter-system communications procedures that evolve over a period of decades or centuries, rather than being scrapped and replaced by human developers starting over again from scratch every few years?
Sure. But are the Facebook chatbots the leading edge of this process?
I seriously doubt it. Are the bots themselves, and their evolved communication procedures, likely to be around in any directly derived form ten years from now?
I’m willing to bet a substantial sum that the answer is “no”.
I probably should have written “…clockwork automata of the 18th century” — I misdated the androids in Adelheid Voskuhl’s work (e.g. Androids in the Enlightenment) by assimilating it to Descartes’ discussion of whether animals are automata.
Mine is circa 1994. Heading off to college in the fall of 2000, I didn't have a computer, so my new roommate offered to give me her old one, which in turn had originally been a salesman's laptop for her father's warehouse. I proceeded to use it pretty heavily my first two years in college (after that, they upgraded and expanded the computer labs, so I could usually find a better open computer there). Considering all that, it's in pretty darn good shape. And it still runs.