anyone know of a good non-neural-network pre-trained word-level language model that's performant and can give me the perplexity of a sentence?
I say "pre-trained" and by that I mean "maybe a database of 2-gram frequencies idk"
ｃｙｂｒｅｓｐａｃｅ: the social hub of the information superhighway
jack in to the mastodon fediverse today and surf the dataflow through our cybrepunk, slightly glitchy web portal
support us on patreon or liberapay!