Natural Language
Derive insights from unstructured text using Google machine learning.
Insightful text analysis
Natural Language uses machine learning to reveal the structure and meaning of text. You can extract information about people, places, and events, and better understand social media sentiment and customer conversations. Natural Language enables you to analyze text and also integrate it with your document storage on Cloud Storage.
AutoML Natural Language
Train your own high-quality machine learning custom models to classify, extract, and detect sentiment with minimum effort and machine learning expertise using the AutoML technology. You can use the AutoML Natural Language UI to upload your training data and test your custom model without a single line of code.
Natural Language API
The powerful pre-trained models of the Natural Language API empowers developers to easily apply natural language understanding (NLU) to their applications with features including sentiment analysis, entity analysis, entity sentiment analysis, content classification, and syntax analysis.
Healthcare Natural Language
Healthcare Natural Language API specializes in helping you find, assess, and link the medical knowledge in your text data, and AutoML Entity Extraction for Healthcare provides you with the ability to generate high-fidelity custom information extraction models for healthcare and life sciences applications. Sign up for early access here.
Natural Language API demo
How AutoML Natural Language works
Benefits
Insights from customers
Use entity analysis to find and label fields within a document — including emails, chat, and social media — and then sentiment analysis to understand customer opinions to find actionable product and UX insights.
Multimedia and multilingual support
Combine Natural Language with our Speech-to-Text API to extract insights from audio conversations. Use it with optical character recognition (OCR) in our Vision API to understand scanned documents. Extract entities and understand sentiments in multiple languages with our Translation API.
Extract key document entities that matter
Use custom entity extraction to identify domain-specific entities within documents — many of which don’t appear in standard language models — without having to spend time or money on manual analysis.
Receipt and invoice understanding
Entity extraction can identify common entries in receipts and invoices — dates, phone numbers, companies, prices, and so on — to help you understand the relationships between a request and proof of payment. It even validates addresses with Google Maps.
Content classification relationship graphs
Classify documents by common entities, domain-specific customized entities, or 700+ general categories, like sports and entertainment. Syntax analysis can help you build relationship graphs of the entities extracted from news or Wikipedia articles.
Best of Google deep-learning models
The Natural Language API offers you the same deep machine learning technology that powers both Google Search’s ability to answer specific user questions and the language-understanding system behind Google Assistant.
Which Natural Language product is right for you?
You can work with either one or reap the benefits of both products by using Natural Language API to quickly reveal the structure and meaning of text — using thousands of pretrained classifications — and using AutoML Natural Language to classify content into custom categories to suit your specific needs.
| AutoML Natural Language | Natural Language API | |
|---|---|---|
|
Integrated REST API Natural Language is accessible via our REST API. Text can be uploaded in the request or integrated with Cloud Storage. |
||
|
Syntax analysis Extract tokens and sentences, identify parts of speech and create dependency parse trees for each sentence. |
||
|
Entity analysis Identify entities within documents — including receipts, invoices, and contracts — and label them by types such as date, person, contact information, organization, location, events, products, and media. |
||
|
Custom entity extraction Identify entities within documents and label them based on your own domain-specific keywords or phrases. |
||
|
Sentiment analysis Understand the overall opinion, feeling, or attitude sentiment expressed in a block of text. |
||
|
Custom sentiment analysis Understand the overall opinion, feeling, or attitude expressed in a block of text tuned to your own domain-specific sentiment scores. |
||
|
Content classification Classify documents in 700+ predefined categories. |
||
|
Custom content classification Create labels to customize models for unique use cases, using your own training data. |
||
|
Multi-language Enables you to easily analyze text in multiple languages including English, Spanish, Japanese, Chinese (simplified and traditional), French, German, Italian, Korean, Portuguese, and Russian. |
||
|
Custom models Train custom machine learning models with minimum effort and machine learning expertise. |
||
|
Powered by Google’s AutoML models Leverages Google state-of-the-art AutoML technology to produce high-quality models. |
||
|
Spatial structure understanding Use the structure and layout information in PDFs to improve custom entity extraction performance. |
||
|
Large dataset support Unlock complex use cases with support for 5,000 classification labels, 1 million documents, and 10 MB document size. |
Our Customers
As part of our goal to accelerate the process of doing business, we help our customers add new documents to DocuSign to get signatures and collect information. Traditionally, they would manually ‘tag’ those documents to show people where to input and where to sign... By using custom entity extraction within AutoML Natural Language, we can use large data sets to train our model and continually improve the process, no matter where the document comes from.
— Kiran Kaza, Head of Mobile Engineering, DocuSign
In the newsroom, precision and speed are critical to engaging our readers. Google Cloud Natural Language is unmatched in its accuracy for content classification. At Hearst, we publish several thousand articles a day across 30+ properties and, with natural language processing, we're able to quickly gain insight into what content is being published and how it resonates with our audiences.
— Naveed Ahmad, Senior Director of Data, Hearst
The team here at Meredith is always looking for better ways to manage our content. We are looking forward to using AutoML Natural Language to apply our custom universal taxonomy to our content. AutoML Natural Language allows us to create custom models that meet our specific needs, with higher accuracy than other solutions that we considered.
— Grace Preyapongpisan, Vice President of Business Intelligence, Meredith
(world-renowned brands such as Martha Stewart and Time Magazine)
Classifying Opinion and Editorials can be time-consuming and difficult work for any data science team, but Cloud Natural Language was able to instantly identify clear topics with a high-level of confidence. This tool has saved me weeks, if not months, of work to achieve a level of accuracy that may not have been possible with our in-house resources.
— Jonathan Brooks-Bartlett, Data Scientist, News UK
Through an employee stress coaching app, we helped our client use custom sentiment analysis in AutoML Natural Language to assess and analyze stress indicators and feelings in a chatbot experience. This technology enabled us to iterate through very quickly to provide an engaging and empathetic consumer experience. This will be an integral product to be used on future projects which require customised sentiment analysis, due to the speed of development and accuracy of the predictions.
— Jason Quek, CTO, Avalon Solutions
We decided to use Google Cloud’s AutoML Natural Language because it reduces overfitting with limited training samples and can scale easily to fit more document types over time. We were able to quickly deploy AutoML Natural Language for custom classification, and down the road we believe we could use the AutoML Natural Language custom entity extraction feature to help with specific use cases like contract review and mortgage data validation.
— Anwar Chaudhry, Director Artificial Intelligence & Machine Learning, Iron Mountain
Pricing
| Natural Language products | Pricing guide |
|---|---|
| Natural Language API | Documentation |
| AutoML Natural Language | Documentation |
Resources
Natural Language docs
Next’ 19: Learn how customers are using the latest Natural Language updates
Natural Language API pricing
AutoML Natural Language pricing
Get started
AutoML Natural Language
Create a custom machine learning model to classify content into domain-specific categories.
Natural Language API
Create a pre-trained machine learning model to reveal the structure and meaning of text.
Products or features listed on this page are in beta. For more information on our product launch stages, see here.
Cloud AI products comply with the SLA policies listed here. They may offer different latency or availability guarantees from other Google Cloud services.