The paper offers a philosophical definition of meaning for AI systems and argues current language models are already 'machines of meaning' but are limited by fixed vocabularies and full-distribution outputs.
Neural Random Projections for Language Modelling
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Neural network-based language models deal with data sparsity problems by mapping the large discrete space of words into a smaller continuous space of real-valued vectors. By learning distributed vector representations for words, each training sample informs the neural network model about a combinatorial number of other patterns. In this paper, we exploit the sparsity in natural language even further by encoding each unique input word using a fixed sparse random representation. These sparse codes are then projected onto a smaller embedding space which allows for the encoding of word occurrences from a possibly unknown vocabulary, along with the creation of more compact language models using a reduced number of parameters. We investigate the properties of our encoding mechanism empirically, by evaluating its performance on the widely used Penn Treebank corpus. We show that guaranteeing approximately equidistant (nearly orthogonal) vector representations for unique discrete inputs is enough to provide the neural network model with enough information to learn --and make use-- of distributed representations for these inputs.
citation-role summary
citation-polarity summary
fields
cs.AI 1years
2024 1verdicts
UNVERDICTED 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Machines of Meaning
The paper offers a philosophical definition of meaning for AI systems and argues current language models are already 'machines of meaning' but are limited by fixed vocabularies and full-distribution outputs.