ELMoForManyLangs
Language embeddings
Provides pre-trained ELMo representations for multiple languages to improve NLP tasks.
Pre-trained ELMo Representations for Many Languages
1k stars
46 watching
243 forks
Language: Python
last commit: over 4 years ago
Linked from 3 awesome lists
elmomultilingualnlp
keon/awesome-nlp
separius/awesome-sentence-embedding
oroszgy/awesome-hungarian-nlpRelated projects:
| Repository | Description | Stars |
|---|---|---|
 jiangtong-li/subword-elmo | This is a repository for a subword ELMo model pre-trained on a large corpus of text. | 12 |
 uclanlp/elmo-c | Efficient Contextual Representation Learning Model with Continuous Outputs | 4 |
 talschuster/crosslingualcontextualemb | Enables alignment of word embeddings across multiple languages to facilitate cross-lingual text analysis and machine learning tasks | 99 |
 t-systems-on-site-services-gmbh/german-elmo-model | A pre-trained deep contextualized word representation model trained on a German Wikipedia corpus | 28 |
 vzhong/embeddings | Provides fast and efficient word embeddings for natural language processing. | 223 |
 chengyuegongr/frequency-agnostic | Improves word embeddings by training with adversarial objectives | 118 |
 juliatext/embeddings.jl | Provides access to pre-trained word embeddings for NLP tasks. | 81 |
 microsoft/unicoder | This repository provides pre-trained models and code for understanding and generation tasks in multiple languages. | 89 |
 dfki-interactive-machine-learning/arasif | Provides sentence embeddings for Arabic languages using pre-trained word embeddings and Smooth Inverse Frequency algorithm | 5 |
 largelymfs/topical_word_embeddings | A Python implementation of a topical word embedding technique used in natural language processing and information retrieval. | 314 |
 wangyuxinwhy/uniem | Develops unified sentence embedding models for NLP tasks | 840 |
 yuvalpinter/mimick | A system for approximating word embeddings using character-level neural networks | 153 |
 fursovia/geometric_embedding | An implementation of a non-parameterized approach for building sentence representations | 19 |
 davidnemeskey/embert | Provides pre-trained transformer-based models and tools for natural language processing tasks | 2 |
 languagemachines/frog | An integration of memory-based natural language processing modules for Dutch | 75 |