Here I share reflections on a not-so-failed in-class experiment involving manual annotation and an LLM-based classification task with XLM-RoBERTa https://corpling.hypotheses.org/5645
‘Literally’ the most interesting project ever!
What happens when you ask fifteen Master’s students to annotate the pragmatic uses of a single adverb across eight thousand historical sentences, then train a neural network on their collective judgments? This post chronicles...
Guillaume Desagulier