Introducing Saga: A Natural Language Understanding (NLU) Framework for Insight-Driven Enterprises
Scalable, cost-efficient, easy to use NLU
Enterprises are increasingly seeking innovative systems to better leverage unstructured, natural language content to deliver actionable business insights, improve efficiencies through automation, and create more engaging user experiences.
However, such systems can require decades of development by highly-specialized computation linguistics experts and data scientists, with results that fall short of expectations. We have also found that, for many enterprises, existing technologies are dramatically too narrow (chatbots), too shallow and generic (cloud-based natural language processing solutions), or too costly to develop, deploy, and maintain. What is needed is a framework that allows non-data-scientist users to create customized, domain-specific language models that will not only process but also understand natural language queries and relevant business content to produce an actionable answer. So, just like how our team has built a range of technology assets to address multiple unstructured content challenges that were not solved by commercial or open source technologies, we undertook the development of a powerful framework that would fulfill enterprises’ fast-growing NLP/NLU demands.
We are pleased to introduce Saga – a scalable, easy-to-use natural language understanding framework with automated pipeline construction, state-of-the-art handling of language ambiguity, integrated machine learning, and business-friendly user interfaces for creating and maintaining language models at reasonable costs.
With two patents pending, the innovative Saga NLU framework enables non-data-scientists to create and maintain powerful, flexible, tested, and scalable enterprise language models for user interaction and document understanding. Incorporating many language modeling techniques and machine learning, this user-friendly semantic framework can handle a wide variety of enterprise NLP/NLU use cases. Typical use cases include extracting data values, relationships, and intents from reports or textual descriptions for analysis; high-accuracy text content classification; semantic search with deep understanding; text understanding for end-to-end question/answer systems; and data preparation for Robot Process Automation (RPA).
Saga delivers a number of differentiators that simplify NLP/NLU tasks, support multi-user collaboration, and accelerate speed to outcomes:
- NLU capabilities are powered by Patterns Matching for precision and ease of editing, combined with Machine Learning for broad coverage and automatic learning.
- Patterns are simple to understand, fast, accurate, easy to get started, quick to show value, and work best when no training data is available. NLP output contains business object IDs which are easily integrated into business actions.
- The process of testing and deploying Machine Learning and language models is easily done and managed by non-data scientists as it does not require coding.
- Non-data-scientists can perform most of the NLP/NLU work, providing prepared and “ready to go” data for data scientists to focus on creating better models where needed.
- Companies have full control over solution performance, deployment (cloud or on-premise), and cost predictability.
- Multiple NLP development efforts, algorithms, and language resources are managed and coordinated entirely within the Saga framework.
Contact us to request a Saga demo and see how it can benefit your natural language use cases.
Register for our upcoming webinar to learn more about NLU and Saga.