Could be, but we had this conversation in 2011 when I first wrote my book. I wrote a lot of detail about the Calgary corpus because it is cited in papers going back 30 years, and less about newer benchmarks. Sami seemed very sensitive to any perceived criticism by me of his work (which I thought was quite good). I did expand my brief mention to a whole section on his benchmark at his insistence after he accused me of being biased against his work. (I did write a lot about my own benchmarks, so I suppose he was right). But the fact is he has not updated his benchmark since 2012 and nobody else uses it, just like too many other newer benchmarks that were abandoned.
I don't know what Sami is doing now. With his technical skills I am sure he could be very successful.