–I’m your alt-right girl. –I want a regular right girl. Someone I can read the National Review with. –The National Review does have the best word scope puzzle. –Yeah, it’s called Henry Kissinger. Actual dialog from a dream in which … Continue reading
You are sitting with your friend Johnny on on his front porch. Johnny pulls two beers out of the cooler next to him and fumbles in his pocket for a bottle opener. “Finally,” he says, “it’s warm enough to sit … Continue reading
On my current NLP project I’ve taken to calling a certain class of data “the text”. This refers to literal text—the natural language I’m being paid to analyze—but also machine learning models, embedding vectors…any string of bits that is useful … Continue reading
A big thing in machine learning-driven artificial intelligence for language processing right now is word embedding vectors. The word cat is represented to the computer not as a string of letters c-a-t, nor as an item in a vocabulary (which … Continue reading
Part of speech. Part of life. Continue reading
My career as an artificial intelligence engineer began in a master’s program in linguistics. There I memorized the International Phonetic Alphabet, played hunt-the-allophone, read the literature on control verbs and code switching, and generally made a good faith effort to … Continue reading
Ferdinand de Saussure: Meaning is difference. Claude Shannon: Difference can be quantified. Alan Turing: Quantification can be automated. Go!