Finite State Automata on Multi-Word Units for Efficient Text-Mining

Text mining is crucial for analyzing unstructured and semi-structured textual documents. This paper introduces a fast and precise text mining method based on a finite automaton to extract knowledge domains. Unlike simple words, multi-word units (such as credit card) are emphasized for their efficiency in identifying specific semantic areas due to their predominantly monosemic nature, their limited number and their distinctiveness. The method focuses on identifying multi-word units within terminological ontologies, where each multi-word unit is associated with a sub-domain of ontology knowledge. The algorithm, designed to handle the challenges posed by very long multi-word units composed of a variable number of simple words, integrates user-selected ontologies into a single finite automaton during a fast pre-processing step. At runtime, the automaton reads input text character by character, efficiently locating multi-word units even if they overlap. This approach is efficient for both short and long documents, requiring no prior training. Ontologies can be updated without additional computational costs. An early system prototype, tested on 100 short and medium-length documents, recognized the knowledge domains for the vast majority of texts (over 90%) analyzed. The authors suggest that this method could be a valuable semantic-based knowledge domain extraction technique in unstructured documents.