Pith. sign in

REVIEW 1 cited by

Neural Random Projections for Language Modelling

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1807.00930 v4 pith:PD54YWJH submitted 2018-07-02 cs.CL cs.NE

classification cs.CLcs.NE
keywords languageneuralencodingrepresentationsspacediscretedistributedenough
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Machines of Meaning

    cs.AI 2024-12 unverdicted novelty 3.0 of 10

    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.

Pith tools