Amazon Comprehend is a natural language processing (NLP) service that uses machine learning to find insights and relationships in text. Amazon Comprehend uses machine learning to help uncover insights and relationships in unstructured data. The service identifies the language of the text; extracts key phrases, places, people, brands, or events; understands how positive or negative the text is; analyzes text using tokenization and parts of speech; and automatically organizes a collection of text…
$0
per unit
TensorFlow
Score 8.5 out of 10
N/A
TensorFlow is an open-source machine learning software library for numerical computation using data flow graphs. It was originally developed by Google.
Specifically, it starts processing millions of documents in minutes by leveraging the power of machine learning without having trained models from scratch. If any of the content contains personally identifiable information not only can Amazon Comprehend locate it but it will also redact or mask it. Using NLP techniques Amazon Comprehend goes well beyond keyword search or rules-based tagging to accurately classify documents. For my task or development, I cannot find any difficulties with Amazon Comprehend.
TensorFlow is great for most deep learning purposes. This is especially true in two domains: 1. Computer vision: image classification, object detection and image generation via generative adversarial networks 2. Natural language processing: text classification and generation. The good community support often means that a lot of off-the-shelf models can be used to prove a concept or test an idea quickly. That, and Google's promotion of Colab means that ideas can be shared quite freely. Training, visualizing and debugging models is very easy in TensorFlow, compared to other platforms (especially the good old Caffe days). In terms of productionizing, it's a bit of a mixed bag. In our case, most of our feature building is performed via Apache Spark. This means having to convert Parquet (columnar optimized) files to a TensorFlow friendly format i.e., protobufs. The lack of good JVM bindings mean that our projects end up being a mix of Python and Scala. This makes it hard to reuse some of the tooling and support we wrote in Scala. This is where MXNet shines better (though its Scala API could do with more work).
Amazon Comprehend identifies the language of the text and extracts Key-phrases, places, people, brands or events.
It can build a custom set of entities or text classification models that are tailored uniquely to the organisation's need
Amazon Comprehend's medical can be used to identify medical conditions, medications, dosages, strength and frequencies from sources like doctor's notes, clinical trial reports and patient health records. This service is very good and with well an accuracy or confidence score.
Theano is perhaps a bit faster and eats up less memory than TensorFlow on a given GPU, perhaps due to element-wise ops. Tensorflow wins for multi-GPU and “compilation” time.
Community support for TensorFlow is great. There's a huge community that truly loves the platform and there are many examples of development in TensorFlow. Often, when a new good technique is published, there will be a TensorFlow implementation not long after. This makes it quick to ally the latest techniques from academia straight to production-grade systems. Tooling around TensorFlow is also good. TensorBoard has been such a useful tool, I can't imagine how hard it would be to debug a deep neural network gone wrong without TensorBoard.
For natural language processing tasks or techniques, there are many service providers out there in the market such as Azure Cloud Services, IBM Watson and Google Cloud Platform (GCP), but compared with them, Amazon Comprehend is the best service provider in contents of accuracy, speed of processing multilingual text, supporting SDK for most of the languages and well documented.
Keras is built on top of TensorFlow, but it is much simpler to use and more Python style friendly, so if you don't want to focus on too many details or control and not focus on some advanced features, Keras is one of the best options, but as far as if you want to dig into more, for sure TensorFlow is the right choice
It supports better and accurately as compared with our existing or old implementations. So, we fulfil our needs as per clients' requirements and it will help to grow or improve client satisfaction.
For these specific requirements, we do not require any machine learning engineers or related professionals to hire in our organisation.
None of any negative sides can be affected our business or distract existing clients.