Next Generation Search Technology - Graph Search Service

To develop scientific and patent text mining tools for students, researchers, and patent experts, we need to understand their daily work, as well as the data they are working with. The latter includes scientific literature, technical and patent documents. Working with them presumes a good understanding of the linguistic characteristics of the text genres. We believe scientific literature, technology and data should be findable to everyone and not just to those who know where to look and how to search. Different types of information requirements need different search solutions such as meta-data search, text-box search, and graph search. To this day, many frequently used text mining methods still superficially postulate that single words taken by themselves, e.g., bag-of-words, can capture the entire scope of a semantic concept. For many text genres and languages, this is a valid premise. However, this is not true for text genres such as those used in patent documents which are characterized by frequent usage of multi-word terms to describe domain-specific concepts (e.g., bus slot card versus double-decker bus). Consequently, many state-of-art text mining techniques, as well as natural language processing tools, show low performance when applied to domain-specific text genres. By integrating domain-specific linguistic information into the text mining pipeline to generate ontologies and full-text indices, Artificial Researcher’s technology provides automatic query expansions with understandable semantic information in order to provide transparent artificial intelligence. The Artificial Researcher Graph Search ServiceTM is a complement to traditional text box and faceted search solutions by allowing users to select a text collection and discover how different terms are related and connected in different text sources.