Information Discovery is a leading Text Mining and Machine Learning platform for businesses that allows you to get insights in your structured and unstructured data and explore important information in the most flexible way.
It allows large amounts of text to be automatically analyzed. In this way we help people to gain new insights, automate demanding routine tasks and make the right decisions by enabling flexible and at the same time powerful data aggregations.
The platform collects and analyzes all types of text documents, e.g. reports, literature, database and filesystem contents and other company internal and external data repositories.
INFORMATION Discovery at a glance
INFORMATION DISCOVERY ALLOWS YOU TO LEVERAGE YOUR DATA FOR BUSINESS-CRITICAL DECISIONS:
- Integrate heterogeneous data from various sources in a single application
- Analyze large amounts of documents in a short time
- Get structured information from free text by using Machine Learning and Natural Language Processing (NLP)
- Retrieve normalized content by mapping to standardized terminologies, thesauri and ontologies
- Discover hidden facts and relations in your data
- Easily drill down your results using advanced filters on top of semantic search
MULTILINGUAL NATURAL LANGUAGE PROCESSING (NLP) & TEXT-MINING
The Text Mining module contains manifold tools of text analysis for the specific extraction of information from documents. We offer several different out-of-the-box NLP annotators that can be used immediately to extract different data for different application scenarios. We support multiple languages. This is particularly important for our partners who want to integrate NLP into their products and want to have a global reach.
MACHINE LEARNING & DEEP LEARNING
We combine the latest deep learning technologies with the world’s most flexible text mining architecture. The document classification module classifies articles and documents automatically into freely-definable categories. Advanced machine learning algorithms learn aspects of human decision making and save valuable time and money in automating otherwise time consuming manual tasks.
TERMINOLOGY MANAGEMENT & SEMANTIC NORMALIZATION
The fully integrated terminology management system allows you to create and import terminological resources, such as thesauri, ontologies, keyword or product lists, etc. In combination with Text Mining, linguistic variants, synonyms, but also multilingualism can be covered, so that the user always has a clear reference to the text.
Information Discovery comes with a high-performance integrated search index, which stores the information resulting from the linguistic and semantic analysis in addition to the plain text. This helps you with your search strategy, because you don’t have to think about different query variations. At the same time, automatic keywording gives you a simple and powerful overview on your data.
Use Information Discovery as your central infrastructure for your Text Mining and Machine Learning tasks. You can simultaneously implement different use cases from different business departments in a single, powerful application.
Use our predefined use cases to ‘AI’ your business
Automated Document Classification
Companies are faced with an overwhelming amount of electronic publications to be collected, archived and indexed in collections and made available to the employees and customers.
This increasing volume in documents cannot be managed any more in forms of intellectual processing.
Averbis supports companies with automated keyword indexing and document categorization of the repositories, to
- significantly reduce the time, effort and costs of indexing
- overcome previous existing indexing gaps in high quality
- better support information retrieval
With the use of freely selectable terminologies and ontologies, keywords and descriptors are automatically extracted from text. Averbis provides a wealth of publicly available terminologies for this task. Text mining technologies identify main headings in documents for content-related structuring and for improved searchability.
Articles and text documents are automatically classified for categorization using freely-definable category systems. Documents and collections may automatically be assigned to the resorts they belong to (e.g. ‘economy’, ‘politics’, ‘medicine’).
PROVISION OF STANDARD AND CUSTOM TERMINOLOGIES
Provide terminological services for your company to ensure semantic interoperability and a uniform exchange of information across businesses. Terminologies play a crucial role whenever specialized knowledge is created, communicated, maintained and accessed. Terminology management has become an integral part of business processes aiming at increasing productivity, quality of products and services and user satisfaction.
Averbis provides world class terminology work for pharmaceutical companies. We provide all relevant standard terminologies for Life Sciences. We also support company tailored und use case specific terminologies for maximum terminology experience.
MAPPINGS BETWEEN TERMINOLOGIES
Terminologies and ontologies declare sets of concepts and relations to encode meaning. They establish a more effective means of capturing and using structured and computable data to improve management of outcomes and reduce costs. Mappings between terminologies serve as semantic glue between applications and help breaking down data silos in companies. They are essential for an effective company-wide information infrastructure. Averbis provides high quality terminology mappings for your most relevant terminologies.
CREATION & ENRICHMENT OF TERMINOLOGIES
All terminologie are not complete and subject to constant change and enlargement. Incomplete terminologies cause negative user experience in terminology-based applications. We enrich terminologies, both automatically and manually. This leads to better data quality, more hits of your searches and more successful applications.
Automatic Verification can assure correctness and compliance. Embedded in your processes it can help you to minimize mistakes or highlight important events e.g. unusual data entries or adverse events.
Scan your surveys, reports, contracts, literature, news, patents,… and get immediate or retrospectively notifications on critical aspects.
Data Quality Check
Subject your documents to a quality check. Use automatic controlled vocabulary to ensure textual information is not only formally correct but also meaningful.
Data Mining and Business Intelligence (BI)
Extract data from different sources and run your BI
Extract and Aggregate information from a variety of document sources. Using entity recognition, concept mapping and relation extraction via Natural Language Processing (NLP) we help you getting insights into your data like never before.
Machine Learning / AI
The document or text classification module of Information Discovery allows customers to create Artificial Intelligence applications based on text data. We provide classification and clustering techniques based on advanced Text Mining and Machine learning algorithms. They can be accessed both via a powerful graphical user interface or with a simple web interface.
Document classification can be integrated with any project through a web API. By this, our customers can implement capabilities to facilitate sentiment analysis, content monitoring, technology categorization, predictive coding, clustering, alerting and concept searching.
SEMANTIC Search & Faceted search
Integrate your own file shares and document management systems and you get value insights into your text based data at a glance.
With our Semantic Search approach you can find specific information in documents with critical business impact. Automated keywording gives you a simple and powerful first overview.
Due to the integration of special components, the search engine offers comprehensive treatment of linguistic phenomenons. Even phrases, synonyms or single components of compound words are recognized and laymen and expert language are normalized.
To reasonably limit the amount of hits, the search engine shows the user related search terms which are semantically associated with the search query.
What our Customers say
We have chosen Averbis as our text mining platform because the solution is highly flexible with an open framework, is a strategic match to our architecture, installed on premise, and proved to be ahead of the competition in our text mining challenge.
Now we are glad to have Averbis as a partner for our pharmaceutical use cases. Averbis showed an agile style of working and a high dedication to quality which brought our project to a fast success.