Likelihood to Recommend 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.
Read full review 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).
Read full review Pros 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. Read full review A vast library of functions for all kinds of tasks - Text, Images, Tabular, Video etc. Amazing community helps developers obtain knowledge faster and get unblocked in this active development space. Integration of high-level libraries like Keras and Estimators make it really simple for a beginner to get started with neural network based models. Read full review Cons It will be great if Amazon Comprehend provide support specifically for litigation or related text documents to extract insights from it. For REST API support using JAVA SDK, it will be great for developers if they provide support for testing without any credentials or account details. Setting up for REST API integration can be as simple as possible. Read full review RNNs are still a bit lacking, compared to Theano. Cannot handle sequence inputs 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. Read full review Usability Support of multiple components and ease of development.
Read full review Support Rating 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.
Read full review Implementation Rating Use of cloud for better execution power is recommended.
Read full review Alternatives Considered 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.
Read full review 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
Read full review Return on Investment 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. Read full review Learning is s bit difficult takes lot of time. Developing or implementing the whole neural network is time consuming with this, as you have to write everything. Once you have learned this, it make your job very easy of getting the good result. Read full review ScreenShots