We are pleased to announce that Cortical.io’s IDP Keyword Extraction has been integrated into Eden AI API.
What is Cortical.io?
Cortical.io is a company specializing in Natural Language Processing (NLP) and Natural Language Understanding (NLU) that offers AI-based solutions to streamline the extraction, classification, review, and analysis of unstructured text data, such as documents, emails, and social media posts.
Their Intelligent Document Processing (IDP) solution, SemanticPro, leverages their NLU and NLP technology to automatically extract and analyze unstructured text, saving organizations significant time and improving compliance by reducing errors in extracted information.
This solution is designed to interpret meaning from text even when the wording varies, making it suitable for accurately searching, comparing, classifying, and analyzing unstructured data like insurance policies, legal documents, and contracts. Cortical.io’s approach to NLU and NLP is based on a patented technology called Semantic Folding, which is recognized for its efficiency, scalability, and smaller environmental impact.
Their solutions have been implemented by Fortune 500 companies across various industries to solve complex challenges involving unstructured documents.
Why do we offer Cortical.io API in addition to other NLP (Natural Language Processing) APIs?
Eden AI offers Cortical.io Keyword Extraction API on its platform amongst several other NLP technologies. We want our users to have access to multiple AI engines and manage them in one place so they can reach high performance, optimize cost and cover all their needs.
There are many reasons for using multiple AI APIs :
Fallback provider is the ABCs.
You need to set up an AI API that is requested if and only if the main AI API does not perform well (or is down). You can use the confidence score returned or other methods to check provider accuracy.
Performance optimization.
After the testing phase, you will be able to build a mapping of AI vendors’ performance that depends on the criteria that you chose. Each data that you need to process will be then sent to the best API.
Cost — Performance ratio optimization.
This method allows you to choose the cheapest provider that performs well for your data. Let’s imagine that you choose Google Cloud API for customer “A” because they all perform well and this is the cheapest. You will then choose Microsoft Azure for customer “B”, a more expensive API but Google performances are not satisfying for customer “B”. (this is a random example)
Combine multiple AI APIs.
This approach is required if you look for extremely high accuracy. The combination leads to higher costs but allows your AI service to be safe and accurate because AI APIs will validate and invalidate each other for each piece of data.
Interview with Cortical.io’s Marketing & Communication Vice-President
What is Cortical.io?
Cortical.io was founded in 2011 in Vienna, Austria, as a research-oriented start-up. Its goal was to investigate an alternative approach to natural language processing (NLP) based on neurosciences. The initial research project, funded by the Austrian government, proved that this method, called Semantic Folding, drastically accelerates the processing of large volumes of text.
Semantic Folding uses a data representation which corresponds to the biological way language information is represented in the human brain: a sparse, distributed vector which encodes all meanings and contexts of a given text — a word, a sentence, a paragraph or even a 200-page book, selecting from a bundle of about 16,000 semantic features. This approach combines both high computing efficiency and high precision — a paradigm shift in an era where large language models impose a trade-off.
What solution do you provide?
Our Intelligent Document Processing (IDP) solutions help businesses extract and classify key information and insights from large volumes of documents, like insurance policies, lease agreements and contracts, as well as text streams such as emails. We focus on enhancing the understanding of unstructured documents by extracting and categorizing key concepts and relationships with our meaning-based approach. Recently, we have started to modularize our solution to meet the increasing demand for composable applications.
Our NLP API was released in January, with first endpoints like keyword extraction, language detection, text segmentation and semantic similarity comparison. Four languages are currently covered (English, Spanish, French, German). Additional NLP functionalities and APIs for document processing will be added in the coming months. Our solutions offer a unique combination of high speed, accuracy, transparency and flexibility — meaning that you don’t need to buy expensive GPUs to classify terabytes of text within seconds. In fact, our technology makes it possible to perform these tasks on a laptop.
Who are your customers?
Over the past decade, we have had the opportunity to work with many Fortune 500 companies around the world, helping them automate their document-centric processes to improve productivity, reduce risks and generate new revenue opportunities. Notably, we have seen an uptake of our solutions in the insurance industry, where automation tool soften fail at accurately processing unstructured content with no pre-defined formats and many language variations.
Our meaning-based IDP software automates the review of complex insurance policies that previously required a lot of time-consuming human intervention. This can save thousands of hours and ensures more timely and accurate quotes. The transportation industry is another reference sector, where our technology can be used to streamline email processing in customer centers or accelerate the processing of shipping documents, leading to productivity gains and higher customer satisfaction.
What motivated you to integrate with Eden AI?
Listing our API on Eden AI helps us increase its visibility and makes it easier for potential users to discover and adopt our technology. We also see this as an opportunity to connect with a community of developers, gather feedback, and foster collaboration. Partnering with an established marketplace like Eden AI will amplify our API’s exposure and will draw more users to our technology.
Last but not least, since Eden AI hosts a variety of APIs, this creates an ecosystem in which developers can discover complementary services. We see a high potential for synergies between different APIs, which encourages developers to build more comprehensive solutions.
How will your product evolve?
We are currently investigating how to leverage some of the capabilities of large language models to add functionalities to our IDP solution, for example to reduce the amount of training required to create custom models. On the API front, we are working on a classification API, that can for example identify offensive language on social media. In the medium term, we plan to expand our API catalogue with several document processing APIs and services.
In the long term, we plan to go beyond natural language processing and solve challenges in other areas like sensor data: Semantic Folding can help to solve the large-scale fusion of sensor data, for example in the manufacturing or automotive industry.
How to use Cortical.io on Eden AI?
To use Cortical.io on Eden AI, you just need to access to the documentation and call the API:
Eden AI is a must-have
Eden AI is the future of AI usage in companies. Our platform not only allows you to call multiple AI APIs but also gives you :
- Centralized and fully monitored billing for all AI APIs
- A unified API for all providers: simple and standard to use, quick switch between providers, access to the specific features of each provider
- Standardized response format: the JSON output format is the same for all suppliers thanks to Eden AI’s standardization work. The response elements are also standardized thanks to Eden AI’s powerful matching algorithms.
- Best Artificial Intelligence APIs of the market: big cloud providers (Google, AWS, Microsoft, and more specialized engines)
- Data protection: Eden AI will not store or use any data. Possibility to filter to use only GDPR engines.
You can see Eden AI documentation here.
Top comments (0)