Text analysis and deep learning: A network approach — mentioned by zwaps

Mon, 10 Apr 2023 08:49:35 GMT

Embeddings can go beyond a contextual definition of meaning. You can use (transformer) LLMs to get a "word sense" aka its predicted probability distribution, which also induces a network of associations (not via context, but via whatever the LLM has learned as fitting words). This gives a structural definition of meaning the ye olde sense (v. Humboldt and so forth). This of course starts with the assumption that LLMs can encode meaning, albeit not in a simplistic linear fashion as Word2Vec or GloVe did https://arxiv.org/abs/2110.04151

Paper and discussion history. A mention is not an endorsement.

Text analysis and deep learning: A network approach · HackerPapers discussions

Text analysis and deep learning: A network approach — mentioned by zwaps