2021/01/27 by Kinjal Basu, Sarat Chandra Varanasi, Basu, Kinjal +7 · 1 citation
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Logic in Computer Science (cs.LO) #Natural Language Processing Techniques #Semantic Web and Ontologies #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2101.11707
openalex publication_date 2021/01/27 · openalex created_date 2022/09/08 · openalex updated_date 2026/07/28
Understanding the meaning of a text is a fundamental challenge of natural\nlanguage understanding (NLU) research. An ideal NLU system should process a\nlanguage in a way that is not exclusive to a single task or a dataset. Keeping\nthis in mind, we have introduced a novel knowledge driven semantic\nrepresentation approach for English text. By leveraging the VerbNet lexicon, we\nare able to map syntax tree of the text to its commonsense meaning represented\nusing basic knowledge primitives. The general purpose knowledge represented\nfrom our approach can be used to build any reasoning based NLU system that can\nalso provide justification. We applied this approach to construct two NLU\napplications that we present here: SQuARE (Semantic-based Question Answering\nand Reasoning Engine) and StaCACK (Stateful Conversational Agent using\nCommonsense Knowledge). Both these systems work by "truly understanding" the\nnatural language text they process and both provide natural language\nexplanations for their responses while maintaining high accuracy.\n