sensegram
Sense embedding analysis tools
Tools and techniques for analyzing word meanings from word embeddings
Making sense embedding out of word embeddings using graph-based word sense induction
212 stars
31 watching
50 forks
Language: Python
last commit: over 5 years agodistributionalembeddingsjobimtextsensesimilaritywordword2vecwsd
Related projects:
| Repository | Description | Stars |
|---|---|---|
 dsv77/hashembedding | Software component providing efficient word representation using hash embeddings | 42 |
 malllabiisc/wordgcn | A deep learning model that generates word embeddings by predicting words based on their dependency context | 291 |
 zhezhaoa/ngram2vec | A toolkit for learning high-quality word and text representations from ngram co-occurrence statistics | 848 |
 jwieting/paragram-word | Trains word embeddings from a paraphrase database to represent semantic relationships between words. | 30 |
 nikhgarg/embeddingdynamicstereotypes | Quantifies 100 years of gender and ethnic stereotypes through word embeddings. | 161 |
 vzhong/embeddings | Provides fast and efficient word embeddings for natural language processing. | 223 |
 xgfs/verse | An open-source implementation of graph embedding from similarity measures | 129 |
 seomoz/word2gauss | This implementation provides a way to represent words as multivariate Gaussian distributions, allowing scalable word embeddings. | 190 |
| jwieting/charagram | A tool for training and using character n-gram based word and sentence embeddings in natural language processing. | 125 |
 m-nasiruddin/wsi4urlang | Develops techniques to induce word senses in under-resourced languages using computational methods. | 0 |
 hassygo/charngram2vec | A repository providing a re-implementation of character n-gram embeddings for pre-training in natural language processing tasks | 23 |
 galuhsahid/indonesian-word-embedding | Demonstrates word embedding in Indonesian language using pre-trained Word2vec models | 20 |
 hslcy/vcwe | This project provides code and corpora for creating word embeddings by considering the visual characteristics of words. | 15 |
 ynqa/wego | An open-source Go library for learning and manipulating vector representations of words | 476 |
 commonsense/conceptnet-numberbatch | A pre-trained word embedding model informed by a large-scale knowledge graph, providing a nuanced representation of word meanings. | 1,296 |