Why there is no “Google Gesture” sign-to-speech translator

Aside from the irresponsible journalism that propagated this story in the first place, the basis for the concept is fundamentally flawed. There cannot be such thing as a wristband a signer can wear that will translate their signed language into spoken language; why? Because signed language is not just on the hands! Signed language is on the face and the body as well. The grammar of signed language is made through eyebrow, mouth, cheek, and even nose movements. Signed language is made with head nods and shakes, head and body tilts, and even shoulder shrugs. Anyone who ever took an introductory course in ASL should know this.

There is one other important flaw in the concept of a gesture-to-speech translation machine, and that is the notion that there is one “sign language.” No, folks, “sign language” is not universal! No sir, no ma’am. Even if Google were able to take input from a human interface device located on a signer’s body–even if that included all the points on the face and body necessary to read signed language–Google would have to add hundreds of signed languages into their Google Translate engine. Language is culture-bound, just as gesture is culture-bound. I’d like to see how this supposed “Google Gesture” would translate the thumbs up gesture, which can mean something like “up yours” in countries other than the United States.

American Sign Language (note that the A in ASL stands for American; i.e., not universal) is a much richer and more complex language than people give it credit for; in fact, so are all the signed languages in the world. Until enough people learn to appreciate the sophistication, complexity, and diversity of signed languages, we will continue to swallow false stories like this hook, line, and sinker.

Translations for CHA-HEAD other than ARROGANT

There is a sign in ASL some call CHA-HEAD because “cha” is the mouth morpheme used in ASL for something big, and the sign for BIG is made around the head level to indicate a “big head” (figuratively speaking). The formal gloss for this sign is ARROGANT (glosses are conventionally written in ALL CAPS). Since ASL has no written form, when people want to write about ASL, or talk about it in English, they assign glosses to signs. The benefit of these glosses is they give us a way to transcribe ASL for the purposes of notation and translation. The drawback of these glosses is they tend to limit our translation of these signs that one gloss, rather than to what the signs actually mean in context.

as any good interpreter or translator knows, words and signs in one languages do not always have single word/sign equivalents in another

One example of a gloss that I believe limits our vocabulary is the gloss ARROGANT for the sign, well, let’s call it CHA-HEAD for lack of a better word other. The thing we might forget is that CHA-HEAD often doesn’t mean anything as extreme as arrogant. A few cases in point: I was interpreting a video relay call some years ago (and of the thousands of call I interpreted in seven years, this is one that stands out), and a Deaf brother signed to his hearing brother something to the effect of YOU CHA-HEAD TELL DAD. I (unfortunately) voiced, “it was arrogant of you to tell him.” The hearing brother said, “I’m not arrogant!” I realized at that moment is was my interpretation, not what his brother said, that he was responding to. I asked the Deaf caller to hold just a moment, and I explained to the hearing caller, “this is the interpreter— sorry about that interpretation. A better interpretation would have been, “you shouldn’ta done that.” I chose that interpretation on second thought because that’s what the Deaf person’s utterance “felt” like when I saw it; in other words, that was the sense of what the Deaf person signed. I had made the mistake of interpreting the form of the word I had been taught for that sign, and the translation was woefully off. When I really thought about it for a moment (and how many “moments” do we really have when we are interpreting a phone call?), I realized not only did the sign not mean arrogant; it really didn’t even translate to a particular word, but more to an expression.

Another case in point, which brought this up for me recently: I was debriefing with a fellow interpreter, and I felt I needed to call them out on something they did on the job that I felt was less than appropriate (as I’ve said, I believe interpreting teams need to be blunt with each other for the sake of consumers. We were conversing in both our languages (as bilingual people often do), and I said, “I thought that was a little [switching to ASL without mouthing] CHA-HEAD.” My colleague said, “it wasn’t arrogant!” Now, you have to understand, this colleague is an intelligent, well-educated, and seasoned interpreter, so if they thought of the word arrogant when confronted with that sign, it tells me the connotation is well entrenched among ASL-English interpreters. What I said to them was, “well, I didn’t mean arrogant; I just meant kind of liberal [in the demand-control schema sense of favoring action as opposed to inaction].” I just felt that they had done something that overstepped an interpreter’s bounds a bit. Of course, that is arguable, and the point is not which one of us was “right” or “wrong”— the point is that my colleague took exception to my ASL sign because of the denotation assigned to it by the English gloss.

A Thesaurus of Translations for CHA-HEAD other than ARROGANT

Since the sign in question means so many things milder than arrogant, here is a list of translations with a range of meanings to match a range of situations. Note these are not all single words, because as any good interpreter or translator knows, words and signs in one languages do not always have single word/sign equivalents in another. These translations are context-dependent, and are not by any means suggested to be one-size-fits-all. Pick and choose what suits the situation. Here’s my list as of now:

  • presumptuous
  • to take it upon oneself to…
  • to go right ahead and…
  • to just…
  • familiar
  • forward
  • to overstep
  • overstepping one’s bounds
  • beyond one’s place
  • crossing the line
  • a bit much, don’t you think?
  • the nerve!
  • to have the nerve to…
  • ballsy
  • cheeky
  • brazen
  • bold
  • conceited
  • big-headed
  • full of oneself
  • taking liberties
  • inappropriate
  • to think [one] can just…

I’m sure the list could go on, but that’s all I can think of at the moment. Do you have any other translations? Please leave a comment. Thanks!

Computerized interpretation of vague language for Web searches

It’s great to see how people other than “interpreters” are implementing the “interpretation” of vague language for practical applications! Panos Alexopoulos, in his presentation Vagueness in Semantic Information Management, discusses how Internet engineers can design databases with search capabilities that can “interpret” what consumers mean when they say they are looking for, say, a “Big, modern restaurant.” (How many square feet is big? What year range or architectural and interior design qualifies as modern?) He discusses the challenge of developing algorithms that can translate vague search terms into specific results. Very interesting!

The many meanings of “hot” and other short words

I was ordering one of those new chicken-and-salad McWraps today, and I asked if the chicken were hot. I had to clarify I meant “hot as in temperature,” not “hot as in spicy.” It got me to thinking about how many meanings there are to the word hot:

  1. High-temperature
  2. Spicy
  3. Stolen
  4. Sexy
  5. Turned on (both sexually and, in the case of a microphone, electronically)
  6. Bright, neon color (like hot pink)
  7. Currently popular (like products that “are really hot right now” or a “hot topic”)
  8. Angry

Thinking about the many meanings of hot (or the “polysemy” of hot, if you will) got me to thinking about other words that are polysemic. Those that came to mind were all one-syllable words: on, cold, run, pan, out… It makes me wonder if it is natural for people to glom onto one-syllable words and load them with meanings so they can use them a lot. After all, it is quicker to use monosyllabic words; they have a punch to them (punch itself being both monosyllabic and polysemous). Polysyllabic words, like extemporaneous and entomological, don’t tend to be polysemic. I Googled “polysemous monosyllabic words” just now to see if linguists have recognized and written about this tendency in language, and I found this:

Because of the well known association between frequency and polysemy on the one hand and frequency and shortness on the other, polysemy should also be a frequent phenomenon in monosyllabic words. (Fenk-Oczlon & Fenk, 2008, p. 59)

So there. I’m not the only one who’s ever noticed this. 🙂

How about you? Have you noticed this phenomenon?

References

Fenk-Oczlon, G. & Fenk, A. (2008). Complexity trade-offs between the subsystems of language. In M. Miestamo, K. Sinnemäki, & F. Karlsson (Eds.) Language complexity: Typology, contact, change, pp. 43-65. Amsterdam, NL: John Benjamins Publishing Co.

Video

Exploding our models to get a better view of our work

I’m not talking about blowing up runway models with dynamite; I’m talking about looking at our work like a 3-D model— stretching it out and viewing its constituent parts from all angles to see how they work together. In the interpreting profession, we talk about “models” of interpretation like helper, conduit, ally, etc. We may have seen some flat diagrams of these models, so maybe we’re used to thinking of models as two-dimensional. How can we bring these models to life and apply them to our work? If you’re like me, you need a picture, or better yet, a moving picture. This video shows the way I like to think of modeling our work. Think of this next time you get supervision or case conference, next time you analyze your work within the Demand-Control Schema. Think of this video and see if you are really taking the time to stretch out the scenario and look at all the parts that make it tick.