You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
New Keras feature: the TextVectorization layer. It takes as input strings and takes care of text standardization, tokenization, and vocabulary indexing. This enables you to create models that process raw strings. End-to-end text classification example: https://colab.research.google.com/drive/1RvCnR7h0_l4Ekn5vINWToI9TNJdpUZB3 …pic.twitter.com/FxCiTRbJU5
Key features: - Supports sparse outputs (int sequences), to be fed into an Embedding layer - Supports dense outputs (binary, tf-idf, count) - Built-in ngram generation Full credits to Mark Omernick for the code example and doing much of the work on this project.
Such a layer makes your text-processing model end-to-end: ingests strings, outputs classes/etc. You can deploy your model without worrying about the external preprocessing pipeline.
Does it take a list of strings, or a list of lists? #realQuestions
It takes a tf.string tensor or ragged tensor.
awesome! Reminds me of some of gensim’s preprocessing features
This is slick 
Thank U!!!!!
This is beautiful! Im glad we're moving toward a lot of preprocessing and data sanitation steps being done as layers.
I love this!!!
This is a nice improvement, though I hope Keras team is looking at Lucene/SOLR for more good ideas on auto-processed text fields. @gsingers
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
