Login / Signup
Opening the Black Box: Analyzing Attention Weights and Hidden States in Pre-trained Language Models for Non-language Tasks.
Mohamad Ballout
Ulf Krumnack
Gunther Heidemann
Kai-Uwe Kühnberger
Published in:
CoRR (2023)
Keyphrases
</>
black box
language model
pre trained
language modeling
hidden states
hidden markov models
document retrieval
probabilistic model
speech recognition
n gram
information retrieval
mixture model
test cases
transfer learning
conditional random fields
natural language
generative model
small number
knn
state space
data sets