Hypothesis Transformation and Semantic Variability Rules Used in Recognizing Textual Entailment

Adrian Iftene, Alexandra Balahur-Dobrescu

Abstract: Based on the core approach of the tree edit distance algorithm, the system central module is designed to target the scope of TE -- semantic variability. The main idea is to transform the hypothesis making use of extensive semantic knowledge from sources like DIRT, WordNet, Wikipedia, acronyms database. Additionally, we built a system to acquire the extra background knowledge needed and applied complex grammar rules for rephrasing in English.