Select Page


Poolparty and QAnswer join technologies to build a Q/A machine on top of your Enterprise Knowledge Graph.

“Alexa, how’s the weather today?” or “Hey Siri, how many grams are in a cup?” are some of the most asked questions to these well-loved virtual assistants, which can respond in “normal” dialogue despite being machines. The power of this dialogue is the fact that it’s built on advanced machine learning technologies, such as question-answering systems (QA), to process and understand verbal questions and respond in relevant natural language instead of returning entire documents or web pages.

In the business world, a solution that combines natural language processing (NLP) techniques with semantic knowledge graphs is proving to be extremely effective. The knowledge graphs, which serve as a malleable and highly intelligent representation of data, can be accessed via NLP that interprets the user’s request and converts it into a response. Using PoolParty Semantic Suite that has been integrated with the QA Company’s QAnswer, you can build and access these conversational AI solutions to vastly improve customer experience on your search platforms. 

Approach Architecture

The biggest challenges for organizations who are not utilizing semantic QA systems.


Limited search capabilities

Simple searches or even current QA systems not built off of semantic parsing struggle to provide enriched results to users. They are either limited to exact keyword search or intent detection (the driver behind FAQs) which can only rely on mapping predetermined questions and answers to be successful. The semantic QA system does not need to be mapped since it can infer the context of the question by breaking it down into semantic parts through knowledge graphs and NLP. Since you build this knowledge graph yourself, you can also open your QA system to respond to industry/regional related jargon that may not be understood otherwise.


Restrictive datasets

Many current search platforms can only retrieve results from text-based content that is lying in the backend of your platform. A QA system that is built off of semantic knowledge graphs and NLP can retrieve results based on various formats of data. In the knowledge graph, you can combine spreadsheets, multimedia assets, text documents, etc., to enable a wider and more accurate search.

Useful Resources

Webinar: Have a Conversation with your Data Using Knowledge Graphs & AI.


White Paper: Natural Langugage Processing with PoolParty.

PoolParty Application Gallery: Get ideas and insights on how to use semantic technology.

The biggest changes organizations can leverage with PoolParty’s semantic QA systems.

Question-answering (QA) systems respond to questions that someone can ask in natural language, thus improving overall search performance and customer experience. Another key tangible benefit is the increased operational efficiency gained by reducing call center costs and increasing sales transactions. More recently we have seen a strong developing interest in in-house use cases, e.g., for IT service desk and HR functions.

What if you didn’t have to painstakingly sift through your spreadsheets and documents to extract the relevant facts, but instead could just enter your questions into your trusty search field? This is optimal from the user’s point of view, but transforming business data into knowledge is not trivial. It is a matter of linking and making all the relevant data available in such a way that all employees—not just experts—can quickly find the answers they urgently need within whichever business processes they find themselves. With the power of knowledge graphs and NLP at one’s disposal, enterprise data can be efficiently prepared in such a way that it can be mapped to natural language questions.

Experience the major benefits of semantic QA systems with PoolParty Semantic Suite today.


Quick, accurate solutions

Combined with QAnswer, our approach does not require thousands of training data to work effectively, which means that the robustness of the QA system does not have to rely on the quality of training examples. Our solution offers high precision and recall by simply plugging your knowledge graph into the QA platform, and it is very flexible in its handling of mistakes in questions written by users. For usability, the QA platform relies on a simple Yes/No user input to the question “Is this the right answer?” to train the system how to respond well to natural language queries.


PoolParty’s adaptable platform allows you to scale your data model as you go. Any updates to your knowledge graph can be done quickly and efficiently. Along with internal information and content, you can also continue to add from external sources such as graph databases and stores to build your knowledge graph further. The QA system will support your knowledge graph’s growth, becoming more intelligent itself.

Strong multilingual abilities

Many search engines and QA systems are held back by their inability to read and respond to different languages. Our approach supports extracting and linking concepts from structured and unstructured data in various languages, which results in the creation of a multilingual knowledge graph that is also able to answer user queries written in a language different from the original source.

Download the white paper