GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → hengluchang → visualizing_contextual_vectors

hengluchang / visualizing_contextual_vectors

Licence: MIT license
Visualizing ELMo Contextual Vectors for Word Sense Disambiguation

Programming Languages

python
139335 projects - #7 most used programming language

Labels

visualizationnlpmachine-learningelmo

Projects that are alternatives of or similar to visualizing contextual vectors

naacl2019-select-pretraining-data-for-ner
BiLSTM-CRF model for NER
Stars: ✭ 15 (-11.76%)
Mutual labels:  elmo
NLP-paper
🎨 🎨NLP 自然语言处理教程 🎨🎨 https://dataxujing.github.io/NLP-paper/
Stars: ✭ 23 (+35.29%)
Mutual labels:  elmo
embedding study
中文预训练模型生成字向量学习，测试BERT，ELMO的中文效果
Stars: ✭ 94 (+452.94%)
Mutual labels:  elmo
Simple-Sentence-Similarity
Exploring the simple sentence similarity measurements using word embeddings
Stars: ✭ 99 (+482.35%)
Mutual labels:  elmo
simple elmo
Simple library to work with pre-trained ELMo models in TensorFlow
Stars: ✭ 49 (+188.24%)
Mutual labels:  elmo
ADL2019
Applied Deep Learning (2019 Spring) @ NTU
Stars: ✭ 20 (+17.65%)
Mutual labels:  elmo
ELMO-NLP
ELMO在QA问答，文本分类等NLP上面的应用
Stars: ✭ 15 (-11.76%)
Mutual labels:  elmo
SIFRank
The code of our paper "SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model"
Stars: ✭ 96 (+464.71%)
Mutual labels:  elmo

visualizing_contextual_vectors

Visualizing ELMo Contextual Vectors for Word Sense Disambiguation. Check out the medium blog post here!

Pre-reqs

Python 3.6

How to install

pip install -r requirements.txt

How to run

python elmo_vis.py to visualize elmo contextual vectors of three words - bank, work, and plant.

References

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].