Parantak Singh
Parantak Singh
Greetings, I am Parantak, a final year CS undergrad. This specific challenge seems interesting and it falls within the domain of my prior endeavors. I'd like to contribute to this....
@someshsingh22 , I know it isn't a true metric, but then the thing is it captures a swap perfectly (in our case the swap perturbation), without allowing that subsequence to...
I am not sure if this would be feasible but introducing an option for the different available embeddings could be done. The attacker should have an option, if possible, depending...
@someshsingh22 , I believe we could start by creating a common class for this inside decepticonlp/preprocess, and then start by implementing a class for each of the separate practices. Does...
Refer to #75
okay!
https://math.mit.edu/classes/18.417/Slides/alignment.pdf http://sepwww.stanford.edu/public/docs/sep112/bob2/paper_html/node3.html http://web.archive.org/web/20081224234350/http://www.dcs.shef.ac.uk/~sam/stringmetrics.html#needleman
@someshsingh22 Right, sorry. I vaguely remembered them both. I searched a bit, and I believe Smith-Waterman is a local alignment algorithm whereas Needle-Wunsch is a global alignment algorithm. So, I...
@someshsingh22 Yeah, of course.
I believe I could add a feature to map digits to their adjacents, and special characters to their adjacents. But I suppose replacing alphabets with special characters won't make a...