Google Releases TensorFlow.Text Library For Natural AI Language Processing

Google Releases TensorFlow.Text Library for Natural AI Language Processing

by Alan Jackson — 4 years ago in Development 2 min. read

Google has unveiled TensorFlow, a newly launched TensorFlow.Text (TF.Text) to preprocess the language model using the company’s end-to-end open source platform for machine learning (ML).

There is a subgroup of keras, but not the width of TF.Text. We are actively talking with them to fill in the gaps that we believe language engineers want, but are not provided in the core Keras API, and I wouldn’t be surprised if in the future additional Kerus layers by TF.Text Are provided.

“TensorFlow offers a wide breadth of ops that greatly aid in building models from video and picture. However, there are huge models that start with text and the language models built from these require some preprocessing before the text can be fed into the model,” describe Robby Neale, software engineer at TensorFlow.

“TF.Text… is designed to ease this issue by providing ops to handle the preprocessing constantly found in text-based models, and other features useful for language modeling not provided by core TensorFlow,” he added.

With TF.Text clients can use tokens to break separated and examine text like words, numbers and accentuation. It can perceive void area, Unicode content and foreordained groupings of word pieces, or “wordpieces, for example, postfixes or prefixes, a technique it has utilized before in program’s, for example, its pretraining technique for language models, BERT. The library can be introduced utilizing PIP.

The introduction of TF.Text pursues only days after the beta arrival of TensorFlow 2.0 which uses less APIs, more profound Keras reconciliation and upgrades to runtime for Eager Execution.

Also read: – Google Launches ‘Live View’ AR Walking Directions for Google Maps

Also read: – Google Street powers Artificial Intelligence tool to Monitor Road Infra

TF.Text is not the first dedicated library to use ML that Google has brought in of late. Last month, the company launched TensorFlow graphics for graphics and 3D models in a more in-depth learning effort.

Alan Jackson

Alan is content editor manager of The Next Tech. He loves to share his technology knowledge with write blog and article. Besides this, He is fond of reading books, writing short stories, EDM music and football lover.

Notify of
Inline Feedbacks
View all comments

Copyright © 2018 – The Next Tech. All Rights Reserved.