The tasks of extracting facts from text
EKG Language Processing is a tool for extracting facts from text. Here are examples of tasks that can be solved using it:
- automatic processing of messages to the technical support service: classification, determination of mass problems and failures, determination of the subject of the request, and so on;
- analysis of contractual documents: identification of the parties to the contract, subject matter of the contract, scope of obligations, additional terms and conditions;
- analysis of organizational and administrative documents, as well as standards and other regulatory documentation: search for definitions of terms, requirements, responsibilities - including for duplications or contradictions;
- extracting facts from various text reports, policy briefs, publications, etc.
Addressing such challenges will allow businesses to:
- save the time employees spend reading and analyzing documents,
- Increase accessibility of information (you may not be able to find the document or fact you need manually),
- enrich the contents of corporate databases, collect more information for analysis,
- speed up the processing of customer requests, improve the quality of organizational and administrative documents,
- automate the control of compliance with the requirements of these documents.
Our product has commercial use cases and brings real value to organizations!
We recommend reading a detailed description of using our product to classify calls to tech support.Our technology and benefits
The uniqueness of our solution lies in the fact that it relies on grammatical parsing of each phrase of the document, moves from the word level to the concept level, and extracts accurate facts from the text. The probability of error with this method of processing is extremely low, while the value and accuracy of the result is high. This allows us to solve even tasks that are not yet possible with large language models (LLM), which only generate a probabilistic answer to a certain question, or with other NLU (Natural Language Understanding) tools, which are mainly reduced to fuzzy tools for statement classification. Our approach is more private (narrow), but much better suited for business problems where the cost of error is high. We know of many examples where LLM “hallucinations” have resulted in serious business losses. Our product does not hallucinate!
The algorithm of operation of EKG LP is as follows:
- extract plain text from the analyzed document (PDF, office formats)
- grammatical analysis of each phrase of the document
- determine whether each phrase or group of phrases belongs to the type of phrase you are looking for: definition, requirement, obligation, error message, etc.
- form a “semantic portrait” of a statement - a formalized structure that conveys its meaning
- replace lemmas with concepts in the “semantic portrait”
- perform the required processing: find duplicates or contradictions, classify statements, record the extracted information in a database, generate answers to questions, and so on.
