Search Results for « Natural language interface »

In this paper, we discuss a natural language interface to a database of structured textual descriptions in the form of annotations of video objects. The interface maps the natural language query input on to the annotation structures. The language processing is done in three phases of expectations and implications from the input word, disambiguation of noun implications and slot-filling of prepositional expectations, and finally, disambiguation of verbal expectations. The system has been tested with different types of user inputs, including ill-formed sentences, and studied for erroneous inputs and for different types of portability issues.

Despite the growing adoption of Property Graph Databases, like Neo4j, interacting with them remains difficult for non-technical users due to the reliance on formal query languages. Natural Language Interfaces (NLIs) address this by translating natural language (NL) into Cypher. However, existing solutions are typically limited to high-resource languages; are difficult to adapt to evolving domains with limited annotated data; and often depend on Machine Learning (ML) approaches, including Large Language Models (LLMs), that demand substantial computational resources and advanced expertise for training and maintenance. We address these limitations by introducing a novel dependency-based, training-free, schema-agnostic Natural Language Interface (NLI) that converts NL queries into Cypher for querying Property Graphs. Our system employs a modular pipeline-integrating entity and relationship extraction, Named Entity Recognition (NER), semantic mapping, triple creation via syntactic dependencies, and validation against an automatically extracted Schema Graph. The distinctive feature of this approach is the reduction in candidate entity pairs using syntactic analysis and schema validation, eliminating the need for candidate query generation and ranking. The schema-agnostic design enables adaptation across domains and languages. Our system supports single- and multi-hop queries, conjunctions, comparisons, aggregations, and complex questions through an explainable process. Evaluations on real-world queries demonstrate reliable translation results.

The paper proposes a new, empirically validated approach to democratizing complex project data for IT executives and senior business stakeholders using a Generative AI-driven natural language interface. The proposed system empowers users to leverage conversational language in querying project data, closing gaps in the accessibility of relevant data, accuracy of decisions, and operational efficiency. It combines advanced handling of natural language processing and understanding, data integration, query mapping, response generation, and visualization with context awareness and adaptiveness. It also opens potential benefits and future research directions for scalability, contextual personalization, and integration with emerging technologies.