BERT-keras | An easy-to-use BERT in keras via tf-hub | Machine Learning library

by Lsdefine Python Version: Current License: No License

X-Ray Key Features Code Snippets Community Discussions(1)Vulnerabilities Install Support

kandi X-RAY | BERT-keras Summary

BERT-keras is a Python library typically used in Artificial Intelligence, Machine Learning, Tensorflow, Keras, Bert applications. BERT-keras has no bugs, it has no vulnerabilities and it has low support. However BERT-keras build file is not available. You can download it from GitHub.

An easy-to-use BERT in keras via tf-hub.

Support

Quality

Security

License

Reuse

Support

BERT-keras has a low active ecosystem.

It has 11 star(s) with 4 fork(s). There are 1 watchers for this library.

It had no major release in the last 6 months.

BERT-keras has no issues reported. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of BERT-keras is current.

Quality

BERT-keras has 0 bugs and 0 code smells.

Security

BERT-keras has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

BERT-keras code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

BERT-keras does not have a standard license declared.

Check the repository for any license declaration and review the terms closely.

Without a license, all rights are reserved, and you cannot use the library in your applications.

Reuse

BERT-keras releases are not available. You will need to build from source code and install.

BERT-keras has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions, examples and code snippets are available.

Top functions reviewed by kandi - BETA

kandi has reviewed BERT-keras and discovered the below as its top functions. This is intended to give you an instant insight into BERT-keras implemented functionality, and help decide if they suit your requirements.

Tokenize text
Convert to unicode
Split text into tokens
Convert a list of sentences into tuples
Convert a single sentence
Create a full tokenizer from the hub module
Apply gradients
Gets the variable name
Determine whether we should use weight decay
Restore token list
Generate token_inv_pointer for token_list
Tokenize a sentence
Set language
Run the command
Build an Adam optimizer
Return a warmup scheduler
Return input tensor inputs
Sets the product of two files
Converts a sequence of tokens to a sequence of tokens
Download and load dataset
Find all hrefs of a given URL
Sort a CSV file by type
Load vocabulary
Load CoNLL format
Generate word - level labels
Save a csv to a file

Get all kandi verified functions for this library.

BERT-keras Key Features

No Key Features are available at this moment for BERT-keras.

BERT-keras Examples and Code Snippets

No Code Snippets are available at this moment for BERT-keras.

Community Discussions

Trending Discussions on BERT-keras

Improving BERT by training on additional data

QUESTION

Improving BERT by training on additional data

Asked 2019-Oct-02 at 10:59

I have a BERT multilanguage model from Google. And I have a lot of text data in my language (Korean). I want BERT to make better vectors for texts in this language. So I want to additionally train BERT on that text corpus I have. Like if I would have w2v model trained on some data and would want to continue training it. Is it possible with BERT?

There are a lot of examples of "fine-tuning" BERT on some specific tasks like even the original one from Google where you can train BERT further on your data. But as far as I understand it (I might be wrong) we do it within our task-specified model (for classification task for example). So... we do it at the same time as training our classifier (??)

What I want is to train BERT further separately and then get fixed vectors for my data. Not to build it into some task-specified model. But just get vector representation for my data (using get_features function) like they do in here. I just need to train the BERT model additionally on more data of the specific language.

Would be endlessly grateful for any suggestions/links on how to train BURT model further (preferably Tensorflow). Thank you.

...

ANSWER

Answered 2019-Sep-30 at 13:34

Package transformers provides code for using and fine-tuning of most currently popular pre-trained Transformers including BERT, XLNet, GPT-2, ... You can easily load the model and continue training.

You can get the multilingual BERT model:

Source https://stackoverflow.com/questions/58155390

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install BERT-keras

At first, set env variable TFHUB_CACHE_DIR and/or https_proxy for saving pre-train models. We must use the original tokenizer to be compatible with the pre-train weights. And the original optimizer leads to better fine-tuning results. More details are in the examples.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: