VCWE
Word embedding generator
This project provides code and corpora for creating word embeddings by considering the visual characteristics of words.
VCWE: Visual Character-Enhanced Word Embeddings (NAACL 2019)
15 stars
2 watching
6 forks
Language: Python
last commit: over 5 years ago Related projects:
Repository | Description | Stars |
---|---|---|
satwikkottur/visualword2vec | Learning word embeddings from abstract images to improve language understanding | 19 |
malllabiisc/wordgcn | A deep learning model that generates word embeddings by predicting words based on their dependency context | 290 |
cod3licious/conec | A library for training and evaluating a type of word embedding model that extends the original Word2Vec algorithm | 20 |
tca19/dict2vec | A framework to learn word embeddings using lexical dictionaries | 115 |
raduionescu/vlawe-boswe | Software providing representations for text classification based on word embeddings and clustering | 10 |
dsv77/hashembedding | Software component providing efficient word representation using hash embeddings | 42 |
explosion/sense2vec | A Python library that generates contextually-keyed word vectors from text data using a variation of the Word2Vec algorithm. | 1,625 |
vzhong/embeddings | Provides fast and efficient word embeddings for natural language processing. | 223 |
wikipedia2vec/wikipedia2vec | A tool for learning vector representations of words and entities from Wikipedia text data. | 940 |
bigredt/vico | Multi-sense word embeddings learned from visual cooccurrences | 25 |
juliatext/word2vec.jl | A Julia interface to the Word2Vec word embedding algorithm | 61 |
dalinvip/cw2vec | A software framework for learning Chinese word embeddings with stroke n-gram information | 274 |
losyer/compact_reconstruction | This project enables efficient reconstruction of word embeddings by leveraging subword representations. | 9 |
jwieting/paragram-word | Trains word embeddings from a paraphrase database to represent semantic relationships between words. | 30 |
jwieting/acl2017 | A codebase for training and using models of sentence embeddings. | 33 |