Abstract
Natural Language Query interfaces allow the end-users to access the desired information without the need to know any specialized query language, data storage, or schema details. Even with the recent advances in NLP research space, the state-of-the-art QA systems fall short of understanding implicit intents of real-world Business Intelligence (BI) queries in enterprise systems, since Natural Language Understanding still remains an AI-hard problem. We posit that deploying ontology reasoning over domain semantics can help in achieving better natural language understanding for QA systems. In this paper, we specifically focus on building a Schema Aware Semantic Reasoning Framework that translates natural language interpretation as a sequence of solvable tasks by an ontology reasoner. We apply our framework on top of an ontology based, state-of-the-art natural language question-answering system ATHENA, and experiment with 4 benchmarks focused on BI queries. Our experimental numbers empirically show that the Schema Aware Semantic Reasoning indeed helps in achieving significantly better results for handling BI queries with an average accuracy improvement of ~30%
Highlights
Natural Language Query (NLQ) interfaces for information access (e.g., Alexa, Google Assistant, and Siri) have gained popularity in recent times as they allow the end-users to specify their information needs in natural language
Our Focus: Admitting that the fully automated interpretation of natural language queries is AI-hard (Yampolskiy, 2013), we focus on a specific aspect of natural language query interpretation in enterprise settings where ontology reasoning can prove beneficial
ATHENA being an ontology-aware system can utilize SME populated configurations to handle some very basic levels of reasoning like choosing a configured key property for a concept in a select clause or doing aggregation for a configured measure property and etc. but ATHENA fails to extend it to more involved generic cases of reasoning modeled in Reasoning Knowledgebase (RKB), which are often required in analytic queries
Summary
Natural Language Query (NLQ) interfaces for information access (e.g., Alexa, Google Assistant, and Siri) have gained popularity in recent times as they allow the end-users to specify their information needs in natural language. An alternate approach is to utilize domain-specific ontologies and knowledge to translate the input natural language query to an intermediate meaning representation like OQL (Ontology Query Language) (Saha et al, 2016; Sen et al, 2020) or AMR (abstract meaning representation) (Banarescu et al, 2013) that can be converted to the structured query (Saha et al, 2016; Li and Jagadish, 2014) These systems work well only if the user explicitly specifies the information need in the query. Such systems fail to capture and interpret the implicit intents implied in the query
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call