Entity Disambiguation in Natural Language Text Requirements

We consider the problem of terminological ambiguity in requirement specifications arising from term-aliasing, wherein multiple terms may be referring to the same entity in a corpus of natural language text requirements. We consider the case of syntactic as well as semantic aliasing. Syntactic alias identification involves automated generation of patterns for identifying syntactic variances of terms including abbreviations and introduced-aliases. Semantic alias identification includes extracting multi-dimensional features (linguistic, statistical, and locational) from given requirement text to estimate semantic relatedness between terms. Based upon the estimated relatedness and standard language database based refinement, clusters of potential semantic aliases are generated. Results of these analyses with user refinement should lead to generation of entity-term alias glossary and unification of term usage across requirements. We present experimental results assessing the effectiveness of the presented approach using a prototype tool for an automated analysis of term-aliasing in the requirements given as plain English language text.