Send someone bright to a course on artificial intelligence, someone with a pedigree of great bot-work and you get "Kian". In Farsi it means "glory" and,yes I have seen the light.
Amir introduced Kian in an e-mail: "Kian is a three-layered neural network with flexible number of inputs and outputs. So if we can parametrize a job, we can teach him easily and get the job done." If I understand properly what this means, I will stop doing most of the work I have been doing on Wikidata with AutoList. I will not reach three million edits and I will be ever so happy.
Amir's example for a first job: Add P31:5 (human) to items of Wikidata based on categories of articles in Wikipedia. The only thing we need to is get list of items with P31:5 and list of items of not-humans (P31 exists but not 5 in it). then get list of category links in any wiki we want[2] and at last we feed these files to Kian and let him learn. Afterwards if we give Kian other articles and their categories, he classifies them as human, not human, or failed to determine. As test I gave him categories of ckb wiki (a small wiki) and worked pretty well and now I'm creating the training set from German Wikipedia and the next step will be English Wikipedia. Number of P31:5 will drastically increase this week.
I am ever so happy because once we know what an item is, it becomes easy to make all kinds of inferences.
Thanks,
GerardM
No comments:
Post a Comment