EncExp is a set of tools for creating and using explainable embeddings. As with any embedding, the aim is to have a set of vectors that can be associated with tokens, and consequently, an utterance can be represented in the vector space span by the vectors. However, the difference concerning the embedding estimated with GloVe or Word2Vec, among others, is that EncExp associates vectors where each component has a meaning. The component’s value indicates whether the word associated with the component might be present in the sentence.
The component’s meaning is a direct consequence of the procedure used to estimate the embedding. EncExp estimates the embedding by solving $d$ binary self-supervised classification problems, where the label is the presence of a particular token. The classifier used is a linear Support Vector Machine.
1 maintainer
Metadata
1 maintainer
Release files for EncExp 0.1.9
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| encexp-0.1.9.tar.gz | 42.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| encexp-0.1.9-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 91.3 kB
Release files / encexp-0.1.9.tar.gz
| Download URL | encexp-0.1.9.tar.gz |
|---|---|
| Size | 42.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9e5cbb0ac6a17a1222c05887eb4a5ff786d914f8800f8b3a6ffded5696088efd
|
|
BLAKE2b-256 checksum How to use checksums |
acacdff3e800ec93488274b28aed085725fbc3ddb2f302b3bb2b6abc2d9e8802
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
Release files / encexp-0.1.9-py3-none-any.whl
| Download URL | encexp-0.1.9-py3-none-any.whl |
|---|---|
| Size | 48.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c415f746d8227685e5af59c8f41041f75f9f95b8f2db3390697f17fbf048c35c
|
|
BLAKE2b-256 checksum How to use checksums |
dc8bb71b6e178e20070f4eead03021f2542d954208c308e4c69e5618e7947d9d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.12
|
