Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
-
Updated
May 22, 2020 - Python
#
subword-units
Here are 14 public repositories matching this topic...
Morfessor is a tool for unsupervised and semi-supervised morphological segmentation
-
Updated
Jul 31, 2019 - Python
Context-sensitive word embeddings with subwords. In Rust.
-
Updated
Jun 2, 2020 - Rust
Properly handle position-dependent phones in a subword lexicon FST
-
Updated
Aug 20, 2017 - Python
Morfessor FlatCat
-
Updated
Aug 20, 2019 - Python
Semantic role labeling with subwords (character, character-ngram and morphology)
-
Updated
Jan 20, 2020 - Perl
Finalfusion embeddings in Python
-
Updated
Jun 5, 2020 - Python
Cognate-aware morphological segmentation
-
Updated
Aug 20, 2019 - Python
A python package to build a corpus vocabulary using the byte pair methodology and also a tokenizer to tokenize input texts based on the built vocab.
nlp
natural-language-processing
tokenizer
vocabulary
nlp-library
vocabulary-builder
natural-language-understanding
subword-units
bpe
bytepairencoding
subwordtokenization
subwordtokens
-
Updated
May 21, 2020 - Python
A tool for generating sub-word (phone or grapheme) level embeddings from an HTK-style MLF ASR corpus
-
Updated
Oct 11, 2019 - Python
Morfessor EM+Prune
-
Updated
Apr 20, 2020 - Python
Morfessor EM+Prune
python
natural-language-processing
segmentation
neural-machine-translation
word-segmentation
subword-units
subword-segmentation
-
Updated
Apr 20, 2020 - Python
Morfessor demonstration
-
Updated
Mar 13, 2015 - Python
Subword Neural Machine Translation
-
Updated
Feb 6, 2019 - Python
Improve this page
Add a description, image, and links to the subword-units topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the subword-units topic, visit your repo's landing page and select "manage topics."