As you’re likely aware, Apple’s new Siri technology was launched as a beta rather than a final release – a move which is especially rare for Apple. But why was Siri released as a beta? A recent blog post from Benoit Maison sheds some interesting light:
I worked on speech recognition with IBM Research for nearly six years. We participated in DARPA-sponsored research projects, field trials, and actual product development for various applications: dictation, call centers, automotive, even a classroom assistant for the hearing-impaired. The basic story was always the same: get us more data! (data being in this case transcribed speech recordings). There is even a saying in the speech community: “there is no data like more data“. Some researchers have argued that most of the recent improvements in speech recognition accuracy can be credited to having more and better data, not to better algorithms.
In essence, Maison explains that Apple’s reason for releasing Siri as a beta was due to Siri’s high level of complexity, and because Apple could not have tested and tuned the technology themselves prior to a final release. Instead, they’re counting on user feedback to refine and improve the technology. Maison continues:
To improve Siri, engineers must painstakingly look at the requests that she could not understand (in all languages!) and come up with new rules to cope with them. There are probably many, many gaps like “abortion clinic” in the current implementation, which will be fixed over time. When Apple states “we find places where we can do better, and we will in the coming weeks”, they are plainly describing how this process works.
It is important to understand that unlike Apple’s hardware and app designs, Siri’s software could not have been fine-tuned and thoroughly tested in the lab prior to a glorious release. It had to be released in its current form, to get exposure to as much variability as possible all the way from the acoustics to the interpretation of natural language. For each of the funny questions that Apple’s engineers had anticipated, poor Siri has to endure a hundred others.
It’s true that Siri is a bit rough, and certainly far from perfect – but allowing their customers to use (and get hooked on) Siri, and collecting data from millions of users actually using the service is the best and most efficient way to produce a polished end result.
For more information, I highly recommend checking out Maison’s original article, which goes into significantly more detail.
