Wikipedia article on the Lancaster-Oslo-Bergen (#LOB) #corpus of modern [British] #English for #NLP
on 02025-07-25the Brown #Corpus as well as other #NLP corpora are linked here
on 02025-07-25more on the Lancaster-Oslo-Bergen (#LOB) #corpus of modern [British] #English for #NLP
on 02025-07-25Lancaster-Oslo-Bergen ("LOB") #corpus of modern [British] #English for #NLP
on 02025-07-25The March 2016 #Eve Developer Diary, on #cp4e. Apparently now they have versions called “WikiEve” and “GridEve” and a #NLP #UX? Lots of pretty #typography in their screenshots.
on 02016-06-27The homepage of the Porter Stemmer #NLP stemming algorithm, among the most-widely-used stemming #algorithms, with dozens of implementations. Recommends using the Snowball stemmer instead, except for “IR research work involving stemming where the experiments need to be exactly repeatable”.
on 02015-08-15“The Unreasonable Effectiveness of Recurrent #Neural-Networks” for #image-recognition, #NLP language modeling (producing what looks an awful lot like Markov-chain text with slightly better context-free properties), sequential processing for directing attention over an image, etc. Lots of animations and visualizations of RNNs doing their thing. The models are written in #Lua with something called #Torch-7 and run with #GPGPU. Lots of great comments! "unreasonable RNNs"
on 02015-08-15