keras-nlp

keras-nlp copied to clipboard

Add an example to MLMMaskGenerator's docstring to show the best practice

6

[MLMMaskGenerator](https://github.com/keras-team/keras-nlp/blob/master/keras_nlp/layers/preprocessing/mlm_mask_generator.py) is a helpful tool to generate masks for input sequences. The current docstring only has two basic examples, and it would be better for users if we can provide...

chenmoneygithub

Generate documentation for keras-nlp

3

We need to generate symbol documentation and host them keras.io (and tensorflow.org?).

mattdangerw

Adversarial Attacks and Testing the Robustness of Models

2

Branching off from the issue which @aflah02 opened a few weeks ago, https://github.com/keras-team/keras-nlp/issues/39: Is the KerasNLP team interested in implementing adversarial attacks? We could start off with simple attacks on...

abheesht17

BIO/IOB Tagging Text and Vice-a-Versa

13

Are there any plans to add a BIO Tagging Layer to KerasNLP? This layer could take sentences and relevant spans as input and output their BIO representations. BIO Tags are...

aflah02

Add ragged support to SinePositionEncoding

2

We should add support for ragged inputs to the `SinePositionEncoding` layer. Our `PositionEmbedding` layer shows a rough example of how this can be done on [this line](https://github.com/keras-team/keras-nlp/blob/master/keras_nlp/layers/position_embedding.py#L93)

mattdangerw

Add type annotations for TransformerEncoder and TransformerDecoder

6

We would like to use type annotations in KerasNLP. We should add them for the encoder/decoder blocks... https://github.com/keras-team/keras-nlp/blob/master/keras_nlp/layers/transformer_decoder.py https://github.com/keras-team/keras-nlp/blob/master/keras_nlp/layers/transformer_encoder.py

mattdangerw

Arabic Tokenizer

2

The tokenization structure is different from languages like English or other languages that start from left to right, and those language like Arabic and langues that start from right to...

Abdelrahmanrezk

Add Function(s)/Class(es) for Decoding Strategies [Text Generation]

4

Not sure if this is worth implementing, but basically, we can have functions/classes, which users can call in order to get decoded text. As far as I know, we have...

abheesht17

Instead of implementing language specific tokenizers, we can try to look at more robust way of dealing with such problems. We can maybe look at a more robust way, like...

Stealth-py

Add the gMLP Encoder Block

2

The gMLP model is from the paper "[Pay Attention to MLPs](https://arxiv.org/abs/2105.08050)". It has a decent number of citations - around 40. Every Encoder Block merely consists of linear layers, a...

abheesht17