GloVe embedding reader (Gensim)¶
Path | pimlico.modules.input.embeddings.glove |
Executable | yes |
Reads in embeddings from the GloVe format, storing them in the format used internally in Pimlico for embeddings. We use Gensim’s implementation of the format reader, so the module depends on Gensim.
Can be used, for example, to read the pre-trained embeddings offered by Stanford.
Note that the format is almost identical to word2vec’s text format.
Note that this requires a recent version of Gensim, since they changed their KeyedVectors data structure. This is not enforced by the dependency check, since we’re not able to require a specific version yet.
Inputs¶
No inputs
Outputs¶
Name | Type(s) |
---|---|
embeddings | embeddings |
Options¶
Name | Description | Type |
---|---|---|
path | (required) Path to the GloVe embedding file | string |
Example config¶
This is an example of how this module can be used in a pipeline config file.
[my_glove_embedding_reader_module]
type=pimlico.modules.input.embeddings.glove
path=value
Test pipelines¶
This module is used by the following test pipelines. They are a further source of examples of the module’s usage.