rguthrie3/MorphologicalPriorsForWordEmbeddings
Code for EMNLP 2016 paper: Morphological Priors for Probabilistic Word Embeddings
This project helps natural language processing practitioners create more accurate word embeddings, especially for languages with complex morphology like Finnish or Turkish. By incorporating information about word parts (morphemes), it takes raw, pre-tokenized text and generates refined word vectors that better capture semantic relationships. This is useful for computational linguists, NLP researchers, and machine learning engineers working on tasks like machine translation or information retrieval.
No commits in the last 6 months.
Use this if you need to generate high-quality word embeddings that account for the internal structure of words, particularly in languages where words can have many different forms.
Not ideal if you primarily work with languages that have very simple or no morphology, or if you need a pre-trained, off-the-shelf embedding solution.
Stars
53
Forks
12
Language
Python
License
—
Category
Last pushed
Dec 06, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/rguthrie3/MorphologicalPriorsForWordEmbeddings"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
dselivanov/text2vec
Fast vectorization, topic modeling, distances and GloVe word embeddings in R.
vzhong/embeddings
Fast, DB Backed pretrained word embeddings for natural language processing.
dccuchile/spanish-word-embeddings
Spanish word embeddings computed with different methods and from different corpora
ncbi-nlp/BioSentVec
BioWordVec & BioSentVec: pre-trained embeddings for biomedical words and sentences
avidale/compress-fasttext
Tools for shrinking fastText models (in gensim format)