Tag Archives: ISAAC 2012

The Dudes Do ISAAC 2012: Day 5 – Of Language and Linguists

I’ve been an SLP for almost 30 years but my first degree is  in Psychology and Linguistics. I fully intended to become a Psychologist [1] but strayed from the path and ended up in Speech Therapy. Needless to say, my fascination with our profession has always been viewed through a linguistics lens and regular readers will already have detected that. In fact, one of the luminaries of AAC, Sarah Blackstone, for many years believed I was a linguist and not an SLP, and I have been introduced as a linguist at more than one conference.

This is probably why I still like to hang out with real linguists, who are much smarter than I and from whom I continue to learn lots of new stuff. So it’s no surprise that I went along to Wednesday afternooon session entitled Natural Language processing and AAC: Current advances at the interface between technology and communication.

Natural Language Processing


 The presenters were more like a panel, bringing different perspectives on how the application of NLP could help the development of AAC [2]. NLP is a cross-over field of linguistics, artificial intelligence, and computer science that deals with analyzing, understanding and generating the languages that humans use naturally in order to interface with computers in both written and spoken contexts using natural human languages instead of computer languages. The main professional body that exemplifies the scope of NLP is the Association of Computational Linguistics, which publishes the journal, Computational Linguistics, on a quarterly basis. With the latest edition including articles with titles such as A Context-Theoretic Framework for Compositionality in Distributional Semantics, and Learning Entailment Relations by Global Graph Structure Optimization, it’s not a field that SLPs are falling over themselves to join. It’s also not a journal I read regularly but then there are so many journals out there it’s impossible to keep track.

SLPAT logo

The folks were also there to promote awareness of a new special interest group called the SIG for Speech and Language Processing in Assistive Technologies, or SLPAT for short. And yes, if you misread it as “splat,” you’re OK because its members also affectionately call it “splat” as well [3].

For those who wonder what Natural Language Processing might offer to AAC, it’s worth bearing in mind that NLP is already being used in a number of areas that we use daily. If you’ve ever used a web-based translation system to read foreign text, then you’ve made use of NLP. If you’ve ever used a speech recognition system such as Dragon NaturallySpeaking or Microsoft Sync in your car, then you’ve benefited from NLP. And if you’ve scanned a document and had a piece of software convert it to text, you’re seeing NLP in action.

In relation to AAC, a number of research initiatives are already underway. Jeff Higginbotham from the University of New York at Buffalo is working on a “just-in-time” message system that will work with AAC devices to provide web-sourced topic-based content using internet (and intranet) natural language processing techniques. Annalu Waller from the University of Dundee is working on prediction-based phonemic AAC systems  (the PhonicStick®) where NLP algorithms are used to determine which sounds are most likely to follow others. Karl Wiegard and Rupal Patel have been investigating non-syntactic word prediction to create systems that can correct user-generated utterences that have flawed syntax. And at the Health and Science University in Portland, Oregon, Melanie Fried-Oken and her colleagues are working with brain-controlled interfaces and spelling systems, the operation of which can be optimized by using special NLP-based software to improve accuracy and speed of selection.

All of these are currently still in the research phase so you needn’t be asking how much you’ll need to buy one, but it’s research like this that will ultimately lead to products, even if 90% of university projects simply end up as articles in journals or a paper that ends with the immortal lines “much more research is needed.”

And if you’re looking for questions, quite a few turned up at the session, most coming from Melanie Fried-Oken who, as a clinician, really wants to see some practical, hands-on solutions. Here are some – of several –  that interested me;

  • Can NLP help us design systems that can adapt to the actual language used by an individual with an AAC device, and maybe even reconfigure the device as a result of this?
  • Can NLP help in the tracking of the vocabulary, representation, and navigation elements of an AAC system?
  • Can NLP help design systems that identify and end-user’s language level?

These resonate because they are the very same questions my collegues and I have been asking for a couple of years now, and have been slowly working towards. In the field of AAC in general, the notion of automatic data logging is not new and has been available for some time on a number of AAC devices. The fun bit is deciding where next to go with this, and how best to leverage the current data collection methodologies. As soon as there’s something to present to the world, we’ll be happy to share!

Meanwhile, for those interested in finding out more on SIG SLPAT, or even if you want to join, you can go to their web site at www.slpat.org and read about the aims of the group [4]. There’s a special edition of the Computer Speech and Language journal out before the end of the year that will be about NLP and Assistive Technology, and the next SIG-SLPAT conference will be in 2013 in France – somewhere. There will be a call for papers later in the year so get your NLP thinking caps on and dust off that passport…

[1] Just a few weeks before I left for University, a friend of my sister was talking to my local newsagent about my moving and asked what I was going to study. Apparently she told him I was studying to be a psychopath. I sometimes wonder how un-wrong she may have been…

[2] The presenters were Kathy McCoy, University of Delaware; Annalu Waller and Alan McGregor, University of Dundee; and Melanie Fried-Oken and Brian Rourk, Oregon Health & Science University. I apologise if I missed someone.

[3] It’s pretty well impossible not to read SLPAT as “splat,” in the same way that fashion store French Connection: UK used the acronym FCUK on all their advertising, knowing full well that folks word read it otherwise! The company voluntarily stopped using the acronym in 2005, but not before stores such as Bloomingdales refused to handle FCUK branded items.

[4] I did see what would happen if I made an error and typed “splat.org” instead of “slpat.org” and found myself at a rather boring “parking site” with links to paintball activities. More fascinating was the “splat.com,” which took me to the home of the Sizzling Platter restaurant group, whose products include Little Caesars Pizza, Red Robin Gourmet Burgers, Dunkin’ Donuts, and Sizzler Steak House.

The Dudes Do ISAAC 2012: Day 4 – Of Corpora and Concordances

Pittsburgh from Station Square

Pittsburgh from Station Square

Marketing applies as much to conference presentations as it does to selling beans. Or coffee. Or bagels[1]. Picking a good title is more important than the presentation itself. Really, it is. Which explains why my “first-thing-in-the-morning” session was not exactly standing room only. The presentation title was the technically accurate but marketingly disasterous Using Concordance Software and online Corpora in AAC. A much better title would have been Using Velcro and a Free iPad for New Simple Gamechanging Therapy. You see, this has all the buzz words that people scan for when reading a conference program. Free is always a winner; iPad is currently sexy; new suggests you will be surprised and maybe first to do something in your part of the world; Velcro® is something ALL therapists relate to; and game-changer is an over-used, over-hyped, almost meaningless vogue word that can be applied to anything in order to make it sound impressive. People who use the word “game-changer” should be hung, drawn, quartered, and made to read a thesaurus.

But I did, fortunately, hear from a number of folks who told me they wanted to come to the presentation but it clashed with another. It clashed, in fact, with several! So given a finite number of potential attendees divided by the number of sessions, as concurrency goes up, individual session attendence goes down. Therefore for those who were unable to attend, I can at least give you a brief summary of what I was talking about. And for those folks who couldn’t make it to ISAAC 2012 in the first place, I’m also including this link to my PowerPoint files and Resources List via the Dudes’ Dropbox account.

The first thing I covered was the difference between core, fringe, and keyword vocabulary. In AAC, the use of core and fringe is now fairly common but we need to make another distinction for something called keyword vocabulary. Here’s how these three words can be defined:

Core word: A word that has a high frequency of use value that is statistically expected when compared to a large reference corpus.
Fringe word: A word that has a low frequency of use value that is statistically expected when compared to a large reference corpus.
Keyword: A word that has a higher frequency of use which is significantly more frequent than expected when compared to a large reference corpus.

Notice that these definitions do not include any notion of “importance.” A common mistake is for people to say things like, “but Tommy loves Transformers so ‘Optimus Prime’ is an important core word for him.” No, “Optimus Prime” is a keyword for him. It may seem like a trivial distinction but it is useful.  Sure, it may be an “important” word for him” but that still does not make it core. Thus, when people talk about a “personal core” for an individual, they are really talking about a person’s keyword set. It is much better to use this because talking about a “personal core” seems to me to be confusing and changes the definition of core.

The notion of keywords has been taken straight from the field of Corpus Linguistics:

Keywords are words which are significantly more frequent in a sample of text than would be expected, given their frequency in a large general reference corpus. (Stubbs, 2010) [2]

Corpus Linguistics uses large data samples, or corpora, to look for patterns in language. The larger the samples are, the more reflective the data is of “real world” language use. One of the largest online sets of such corpora is those developed and maintained by Mark Davies at Brigham Young University in Utah. The Corpus of Contemporary American English [3] is based on a sample of 425 million words, and can provide frequency data of individual items, as well as contextual information on how these are typically used. This type of data can be useful for the AAC practitioner in determiner which words to include in a system and to answer questions about how a word may be used (e.g. is the work light used more as a noun than a verb?)

Another tool used by corpus linguists is concordance software. Such software allows investigators to input text and create output in the form of frequency lists, key word lists, and key words in context. The AAC practitioner can use client-generated data and run it through concordance software to build personal vocabulary lists. It’s also possible to compare a client’s data with other samples, which can also be very instructive for a clinician who wants to see how an individual’s use of language matches with a “standard.”

Concordance software


Concordance is a flexible text analysis program which lets you gain better insight into e-texts and analyze language objectively and in depth. It lets you count words, make word lists, word frequency lists, and indexes.

You can select and sort words in many ways, search for phrases, do proximity searches, sample words, and do regular expression searches. You can also see statistics on your text, including word types, tokens, and percentages, type/token ratios, character and sentence counts and a word length chart.

Wordsmith concordance softwareWordSmith is a popular word-analysis software that includes features to generate word lists, frequency lists, usage lists, and keyword lists.

It also has the option to download the British National Corpus word frequency list to use as a large comparative data set. This is a great tool for investigating keywords among small data sets.

Now, a number of commercial devices have this data-logging feature included as an option, providing a record of events over time. With the client’s consent, being able to track such usage can be invaluable in helping clinicians and educators see exactly what the client is currently capable of doing and, by extension, create teaching plans that will develop their ability to use the device. But if you are prepared to clean the raw data from an AAC device up a little, you can drop it into a concordance software and works some magic. You can see how a client’s use of vocabulary matches what you might expect; you can discover a clients keyword vocabulary by filtering out core words; and you can look at how client’s use vocabulary in context e.g. where do they use the word light and how is it being used.

In summary, what I’m suggesting is that using (a) large online corpora and (b) concordance software can enhance the way on which we develop and expand AAC systems, and that both of these are based on actual usage of language and not some hypothetical construct of what we think is happening with vocabulary.

Enough of the academic stuff; I just want to alert you to an unmissable experience at Tonic Bar & Grill on the corner at 971 Liberty Avenue, just outside the David L. Lawrence Convention Center. Those of a nervous gastronomic disposition may want to stop reading now – as may folks who are on any diet other than the “Let’s See How Fat I Can Get Before My Arteries Explode” diet.

At any time of day, you should prop yourself up at the bar, order one of their small selection of draught beers, and place an order for Poutine Fries [4]. This is a heavenly bowl of hot potato fries, smoothered in slippery, creamy cheese, and topped with a generous helping of tender braised short ribs. You can choose to experience this ambrosial feast either by eating it or having a cardiologist smear it directly on to your arteries: we recommend the former. How we managed to eat just one bowl is still a mystery to us but our hearts will undoubtedly thank us.

Poutine fries

Poutine Fries

[1] As it was an early presentation, I skipped breakfast, which meant that by the time I’d finished I was hungry. So a shout out to the good folks at Bruegger’s Bagels on Grant Street in downtown Pittsburgh who supplied me with their Breakfast Bagel, a mouth-watering treat of egg, cheese, and bacon on a crusty whole-wheat bagel. I’m pretty sure it’s not the healthiest of starts to the day but it sure is one of the tastiest.

[2] Stubbs, M. (2010). Three concepts of keywords. In M. Bondi and M. Scott (Eds.) Keyness in Texts: Studies in Corpus Linguistics. John Benjamins Publishing: Philadelphia.

[3] Davies, M. (2008-) The Corpus of Contemporary American English: 425 million words, 1990-present. Available online at http://corpus.byu.edu/coca/.

[4] As our Canadian friend will know, Poutine Fries originated in Quebec and therefore represent a form of biological warfare against America, the intent being to bring the country to its knees by making everyone too fat to get up off of them. Rest assured that on their next trip to Montreal, the Dudes will make sure they take advantage of sampling the local Poutine Fries and would encourage anyone taking a trip to Canada to do the same!

The Dudes Do ISAAC 2012: Day 3 – On Dragons, Hammers, and Rooftops

Day 3 was really Day 1 in terms of the main conference, so I had to register like everyone else, even though I’d taught at the pre-conference session. I have to say that the signage at the David L. Lawrence Centre [1] for ISAAC 2012 needs to be commended. The place is huge but I was able to find my way to registration easily, and it only took about a minute from saying my name to leaving the counter.

ISAAC 2012 Registration

Welcome to ISAAC 2012

By sheer coincidence, standing right next to me was #slpeeps very own @bronwynah, who also doubles up as a member of #slpeeps-downunder. It seems that we #slpeeps get everywhere!

We were there to make sure we got our seats for the Opening Ceremony, which turned out to be a rather splendid event with the right amount of gravitas and humor. Guest speakers included Al Condeluci, a Pittsburgh native, born and bred, who has had a lifetime of working with United Cerebral Palsy and is a tireless promoter of rights for all. We also had Peter Yarrow, the singer from the iconic folk trio of the 60’s and 70’s, Peter,Paul & Mary. Yarrow has always been politically active and talked about his involvement in the recent “Occupy” protests. He equated the struggle faced by many people with disabilities as similar to those of African-American Civil Rights Movement in the 60’s and black South Africans led by Nelson Mandela in the 80’s.

Here he plays If I Had A Hammer accompanied by the ISAAC 2012 delegates.

Video courtesy of Teechkidz via YouTube.

Following the opening ceremonies there were a number of sessions during the afternoon, and the closing of the day was marked by the rooftop Welcome Reception on the North Terrace of the Convention Center. This was a ticket-only event based, presumably, on the fact that the number of folks registered would determine the amount of hors d’ouevres available. Tragically, there may have been some gatecrashers because by the time I actually got to the food tables, all that was left we some gazpacho shooters; tiny cups of cold soup that were fighting a losing battle with the 90+ degree temperatures in Pittsburgh.

I admit, there may have been some fault here. When I got to the roof, I saw that the bar line consisted of one person whereas the food line was somewhat longer. It was, after all, almost 6:00 p.m. and so an ice-cold beer was far too tempting to turn down. By the time I’d schmoozed and chatted with folks, the line for the food was still long and the beer line was also long. However, if you have friends at the front of the beer line…

So by the time I made it to the food line, at was gone. Except for the gazpacho. It was only through sheer chance that a colleague later managed to hunt down some brie and crackers, which served to stave off hunger until a group of us made our way to the unpretentious August Henry’s City Saloon on Penn Avenue. Here you can get a large White Russian for $7.00 and a dozen chicken wings for $10.00. Wing lovers might want to note that they offer a selection of dry rub wings in mesquite, ranch, and Caribbean Jerk flavors.

August Henry's City Saloon

August Henry’s

I spent a little time at the bar talking with an old colleague, Cliff Kushler, the inventor of T9 and Swype, about lexical disambiguation [2] and Swype Art. Swype Art, you ask? Well, those of you who use Swype as an input to a smart phone or tablet might like to try to trace out the word “infinity” and see what happens! Here’s a video that shows how the words “banana,” “infinity” and “circles” look on a Swype keyboard.

If you find any other words that have traced pictures that seem appropriate, be sure to share them with us

[1] David H. Lawrence was mayor of Pittsburgh from 1946 to 1959, who then went on to become the 37th Governor of Pennsylvania. He was born in 1889 and died in 1966.

[2] Lexical disambiguation is the process that is going on behind systems such as T9, Swype, SlideIt, TouchPal, and other keyboard accessing programs. The underlying software looks at the key you are selecting and then the subsequent keys, then “guesses” what you might be looking for. For example, if you start with an “B” and move across to “R,” you actually touch either the F or the G keys on the way, but because the system “knows” there are no words in English that start with “Bf” or “Bg” it ignores those an assumes you are looking for a word that begins with “br.” If you then swipe across to the letter “A,” it ignores your sliding across “D,” “S” or “W” because there are no words with “brd,” “brs” or “brw” in English. There are, of course, other factors involved but the basic notion of lexical disambiguation is relatively simple to understand.

The Dudes Do ISAAC 2012: Day 2 – Of Idleness and Imbibing

Regular readers of the Dudes have already discovered that we often wander astray from the topic of Speech Pathology. Some casual readers may already have abandoned us for precisely that reason. We’re sorry about that but we can’t get past the fact that much as we love our jobs, we’re not defined by our profession alone. We’d like to think that this is true of all of us; that being a Speechie is just part of our identity and there is more to life than work.

Which is why on the Sunday afternoon of July 29th, the Dudes ended up propping a bar for seven hours. Yes, you read me correctly – seven hours. OK, in all honesty, only Dude Two was there for that long. I only managed a mere four. And true, we did spend some time poking around with pieces of AAC technology to test new software and hardware features, but if there’s a little space on a bar top, it’s surprising how much you can do while simultaneously taking advantage of a huge wine bar selection.

In one of those wonderfully serendipitous turns of fate that can quickly turn an ordinary day into an adventure, Dude Two, who is staying at the Courtyard by Marriott in downtown Pittsburgh, discovered a door in the hotel that lead directly into an adjacent restaurant; the Sonoma Grille [1]. Being a wine aficionado, finding this location literally on the doorstep proved to be like walking through a wardrobe door into Narnia but instead of finding Mr. Tumnus, he found Tiffany, a skilled and attentive bar tender who was only too happy to help him explore the huge selection of wines on offer. Specifically, he was tempted by a St.Clement 2009 Chardonnay. Indeed more than one.

Sonoma Grille Wine Bar

Sonoma Grille Wine Bar

The Sonoma also has an excellent lunch menu, from which Dude Two enjoyed a lamb pot roast sandwich, which consisted of large chunks of tender lamb on fresh multi-grain bread, generously filled with whipped potato, roasted corn, grilled scallion, a local cheddar cheese, and house-made pickled Serrano peppers.

By the time I made it across, it was clearly time for cocktails. Pittsburgh has a number of local brews available, but the warm, summer afternoon mixed with the continental atmosphere of the bar made a Mojito inevitable.
At some point, afternoon became evening, marked by the menu magically changed from Lunch to Dinner, which meant that a whole new set of scrumptious tucker was available. This time we went for the twin bacon-wrapped medallions of veal, served on top of truffled whipped potatoes, with wild foraged Maitake mushrooms, local pears, crispy sage, and a layer of veal gravy. The wine had now given way to Cuba Libres [2], a much more exotic name for a Bacardi and Coke [3], and therefore more in keeping with the atmosphere.

As an aside, I happened to notice that high up in a case at the back of the bar was a bottle of Remy Martin Louis XIII. This is a particularly special cognac that has to age for anywhere between 40 and 100 years, which means the master distiller who lays down the barrel (or tierçon, as it is called) never gets to taste it. This unique aging process also contributes to the fact that a glass of Louis XIII at the Sonoma Grill is just short of $170. It’s on my bucket list – but not this time.

Remy Martin Louis XIII

Remy Martin Louis XIII

A couple of colleagues joined us for the last hour, which meant it was after 8:30 p.m. by the time we decided to call it a day. I got back to the hotel and tried to read a little more of Haruki Murakami’s 2011 opus 1Q84 but I’m apparently older than I want to believe and nodded off to sleep.

Sometimes, it’s OK to take a day off. Sometimes.

[1] More about the Sonoma Grille, including the all-important menus and wine list, can be found at the web site: http://thesonomagrille.com

[2] Coincidentally, I have just finished reading the 2007 book And A Bottle Of Rum by Wayne Curtis, who offers a number of alternatives for the origin of the name, Cuba Libre. One popular explanation is that in 1900, during the Spanish-American War, an American officer in Cuba ordered a rum mixed with Coca Cola, which made its first appearance there also during 1900. A number of other soldiers saw this and decided to try it out and it became a new favorite. A variation on this simply has a group of Cuban and American soldiers in a bar during the Spanish-American War, all drinking rum and with the Americans toasting their Cuban counterparts by shouting “To a free Cuba!” or “Por Cuba libre!!”

[3] The creator of possibly the world’s most succesful soft drink was a pharmaceutical chemist from Atlanta named John Pemberton. He made it using infusions of the coca plant from the Peruvian Andes and the high-caffeine kola nut from Africa. Like all good cooks and marketing executives, he added seven secret flavoring agents to make it unique and mysterious. Clearly he named the drink after its principal ingredients: hence, Coca-Cola.