Difference between revisions of "Natural Language Tools & Services"

From
Jump to: navigation, search
m
Line 15: Line 15:
 
* [http://github.com/salesforce/pytorch-qrnn PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM | gitHub]
 
* [http://github.com/salesforce/pytorch-qrnn PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM | gitHub]
 
* [http://www.kdnuggets.com/2018/12/activewizards-comparison-speech-processing-apis.html API-based Services]
 
* [http://www.kdnuggets.com/2018/12/activewizards-comparison-speech-processing-apis.html API-based Services]
−
* Capability with [[Javascript]]:
+
==== Capability with [[Javascript]] ====
 
**[[TensorFlow.js]] for training and deploying ML models in the browser and on Node.js (was called Deeplearnjs)  
 
**[[TensorFlow.js]] for training and deploying ML models in the browser and on Node.js (was called Deeplearnjs)  
 
** [http://transcranial.github.io/keras-js/#/ Keras.js] runs Keras models in the browser, with GPU support using WebGL. since Keras uses a number of frameworks as backends, the models can be trained in TensorFlow, CNTK, and other frameworks as well.
 
** [http://transcranial.github.io/keras-js/#/ Keras.js] runs Keras models in the browser, with GPU support using WebGL. since Keras uses a number of frameworks as backends, the models can be trained in TensorFlow, CNTK, and other frameworks as well.
Line 21: Line 21:
 
** [http://compromise.cool/ Compromise] modest natural-language processing (NLP) interprets and pre-parses English and makes some reasonable decisions
 
** [http://compromise.cool/ Compromise] modest natural-language processing (NLP) interprets and pre-parses English and makes some reasonable decisions
 
** [http://github.com/NaturalNode/natural Natural] provides tokenizing, stemming (reducing a word to a not-necessarily morphological root), classification, phonetics, tf-idf, WordNet, string similarity, and more. (nodejs)
 
** [http://github.com/NaturalNode/natural Natural] provides tokenizing, stemming (reducing a word to a not-necessarily morphological root), classification, phonetics, tf-idf, WordNet, string similarity, and more. (nodejs)
−
* Capability (other):
+
==== Capability (other) ====
 
** [http://github.com/zalandoresearch/flair flair] use pretrained BERT (PyTorch)
 
** [http://github.com/zalandoresearch/flair flair] use pretrained BERT (PyTorch)
 
** [http://stanfordnlp.github.io/CoreNLP/ CoreNLP | Stanford] (Python)
 
** [http://stanfordnlp.github.io/CoreNLP/ CoreNLP | Stanford] (Python)

Revision as of 23:01, 6 April 2019

Youtube search... ...Google search

Capability with Javascript

    • TensorFlow.js for training and deploying ML models in the browser and on Node.js (was called Deeplearnjs)
    • Keras.js runs Keras models in the browser, with GPU support using WebGL. since Keras uses a number of frameworks as backends, the models can be trained in TensorFlow, CNTK, and other frameworks as well.
    • NLP.js NLP Manager: a tool able to manage several languages (nodejs)
    • Compromise modest natural-language processing (NLP) interprets and pre-parses English and makes some reasonable decisions
    • Natural provides tokenizing, stemming (reducing a word to a not-necessarily morphological root), classification, phonetics, tf-idf, WordNet, string similarity, and more. (nodejs)

Capability (other)

Retrieved from "https://primo.ai/index.php?title=Natural_Language_Tools_%26_Services&oldid=7095"