NL2SQL method based on Thesaurus and Knowledge-Augmented

Nowadays most of people of developed economy countries interact with software every day. As a result of computer systems expansion to all scope of people's activity the problem of transition from visual and command interfaces to natural language user interfaces is thrown into the sharp relief. Computational linguistics and natural language processing methods are described in this article. Represent a formal definition of a dialogue system as a Markov decision process. Methods of natural language manipulation are applied in machine translation software systems, systems of search and exchange the data, text annotation and expert systems. Prototype of natural language user interface to structured data source is developed. As a result it is convert natural language user's query to SQL query to database. Also showed application of Levenshtein distance for processing natural language query to SQL query to database. Natural language user interface is created to predefined subject field. User interface interacts to database that contain information about existent program libraries and frameworks. Consequently, using natural language processing methods it is possible to develop user natural language user interface providing capability to interact with machine.

Although a great deal of research effort has been expended in support of natural language (NL) database querying, little effort has gone to NL database update . One reason for this state of affairs is that in NL querying, one can tie nouns and stative verbs in the query to database objects (relation names, attributes and domain values). In many cases this correspondence seems sufficient to interpret NL queries. NL update seems to require database counterparts for active verbs, such as hire, schedule and enroll, rather than for stative entities. There seem to be no natural candidates to fill this role.We suggest a database counterpart for active verbs, which we call verbgraphs . The verbgraphs may be used to support NL update. A verbgraph is a structure for representing the various database changes that a given verb might describe. In addition to describing the variants of a verb, they may be used to disambiguate the update command. Other possible uses of verbgraphs include, specification of defaults, prompting of the user to guide but not dictate user interaction and enforcing a variety of types of database integrity constraints.

The goal of the RENDEZVOUS Project is to enable a casual user to access relational data bases in natural language without a preliminary training period. The system will, if necessary, engage in an English dialogue with the user in order to arrive at an unambiguous statement of his query. This dialogue serves the triple purpose of aiding the user in his problem specification, of clarifying ambiguities inherent in the English language and of enabling the system to overcome incomprehensible features of the users query. The conversation must constantly narrow the scope of inquiry, resorting to menu selection if necessary until the user and system come to an agreement as to what information has been requested. At any moment during the dialogue, the system must be capable of expressing its current understanding of the user's query in clear and unambiguous English. In particular, the system must be able to rephrase the user's query for approval before execution.

In this paper, a general architecture is proposed for developing embodied conversational agents with fuzzy ontology knowledge base. The proposed architecture enables agents to interact with the user via multimodal channels in a virtual reality environment for the purpose of language learning. The agents play the role of emotional, rational, and friendly partners who provide a specific domain of knowledge based on user's queries in natural language. These queries are performed by an optimized fuzzy search engine. Two scenarios including two virtual airports and a virtual electronic gadget shop are implemented in this architecture to improve users' oral skills. The results show the users' average oral skills improved 11%. Moreover, 80% of the users ranked agents' logical sequence of actions and the total speed of responses as very good, and 90% of them evaluated agents' appropriateness of responses as very good based on Likert scale.

In the absence of interaction history, image recommendations often depend on content-based approaches. Prompted by user queries in natural language, such systems rank items based on the similarity between textual and visual features. However, these approaches typically rely on static queries and do not offer alternative feedback mechanisms. In this paper, we present VisualReF: an interactive image retrieval prototype that introduces visual relevance feedback through fine-grained user annotations. Built on vision-language models (VLMs) for retrieval, our system allows users to label relevant and irrelevant regions in retrieved images. These regions are captioned using a generative vision-language model to refine the query vector. Our work bridges the gap between conventional static image retrieval and interactive, user-guided search by introducing visual relevance feedback. Finally, our prototype contributes to the field of visual recommendation by empowering researchers with practical tools for: (i) collecting region-level visual relevance signals from users, (ii) supporting integration of human feedback into interactive search pipelines, and (iii) explaining how the relevance feedback model perceives user input.

Financial and economic data are typically available in the form of tables and comprise mostly of monetary amounts, numeric and other domain-specific fields. They can be very hard to search and they are often made available out of context, or in forms which cannot be integrated with systems where text is required, such as voice-enabled devices. This work presents a novel system that enables both experts in the finance domain and non-expert users to search financial data with both keyword and natural language queries. Our system answers the queries with an automatically generated textual description using Natural Language Generation (NLG). The answers are further enriched with derived information, not explicitly asked in the user query, to provide the context of the answer. The system is designed to be flexible in order to accommodate new use cases without significant development effort, thus allowing fast integration of new datasets.

A new method is developed to query a relational database in natural language (NL). The method, based on a semantic approach, interprets grammatical and lexical units of a natural language into concepts of subject domain, which are given in a conceptual scheme. The conceptual scheme is mapped formally onto the logical scheme. We applied the method to query the FlyEx database in natural language. FlyEx contains information on the expression of segmentation genes in Drosophila melanogaster. The method allows formulation of queries in various natural languages simultaneously, and is adaptive to changes in the knowledge domain and user's views. It provides optimal transformation of queries from natural language to SQL, as well as visualization of information as a hyperscheme. The method does not require specification of all possible language constructions as well as a standard grammar accuracy in formulation of NL queries.

The number of databases as well as their size and complexity is increasing. This creates a barrier to use especially for non-experts, who have to come to grips with the nature of the data, the way it has been represented in the database, and the specific query languages or user interfaces by which data are accessed. These difficulties worsen in research settings, where it is common to work with many different databases. One approach to improving this situation is to allow users to pose their queries in natural language. In this work we describe a machine learning framework, Polyglotter, that in a general way supports the mapping of natural language searches to database queries. Importantly, it does not require the creation of manually annotated data for training and therefore can be applied easily to multiple domains. The framework is polyglot in the sense that it supports multiple different database engines that are accessed with a variety of query languages, including SQL and Cypher. Furthermore Polyglotter supports multi-class queries. Good performance is achieved on both toy and real databases, as well as a human-annotated WikiSQL query set. Thus Polyglotter may help database maintainers make their resources more accessible.

Extraction of knowledge data from knowledge database using natural language query is a difficult task. Different types of natural language processing (NLP) techniques have been developed to handle this knowledge data extraction task. This paper proposes an automated query-response model termed Extended Automated Knowledge Provider System (EAKPS) that can manage various types of natural language queries from user. The EAKPS uses combination based technique and it can handle assertive, interrogative, imperative, compound and complex type query sentences. The algorithm of EAKPS generates structure query language (SQL) for each natural language query to extract knowledge data from the knowledge database resident within the EAKPS. Extraction of noun or noun phrases is another issue in natural language query processing. Most of the times, determiner, preposition and conjunction are prefixed to a noun or noun phrase and it is difficult to identify the noun/noun phrase with prefix during query processing. The proposed system is able to identify these prefixes and extract exact noun or noun phrases from natural language queries without any manual intervention.

Qur’anic verse recommender systems are increasingly needed to assist users in understanding the vast and profound contents of the Qur’an through natural language queries. With over 6,000 verses, identifying spiritually relevant content remains a challenge, especially for users who are not familiar with specific keywords, themes, or Arabic vocabulary. This paper proposes a novel hybrid embedding-based recommendation approach that combines Sentence-BERT (SBERT) for semantic sentence-level representation and Term Frequency–Inverse Document Frequency (TF-IDF) for keyword emphasis. This dual embedding strategy allows the system to better understand users’ explicit intents as well as the underlying semantic context of the queries, offering more accurate and meaningful verse suggestions. Unlike traditional recommender systems, this solution does not rely on user history or collaborative filtering, effectively addressing the cold-start problem. The system also integrates a Large Language Model (LLM), specifically LLaMA, to generate contextual and spiritually meaningful explanations in Bahasa Indonesia. These explanations are created using zero-shot prompting, enabling dynamic interpretation of the recommended verses based on the user's query context. The system is deployed via a Telegram bot, enabling broad accessibility and ease of use. Evaluations were conducted through expert review and user testing. Experts rated the relevance and quality of the recommendations with an average precision of 82.4%, while general users provided an average satisfaction rating of 4.37 out of 5 across various dimensions including ease of use, clarity, and relevance. This study contributes to the development of AI-driven religious tools by presenting a method that combines semantic embeddings and LLM-generated explanations for intuitive and reflective interaction with the Qur’anic text. It also demonstrates the potential of hybrid NLP approaches and conversational interfaces in enhancing spiritual learning and access to religious knowledge in the digital age.

Android developers often need to search for example code to complete their development tasks. While existing code search systems for Android can deliver code against a search query, they do not recommend code for features that a developer might later need to implement. In this paper, we present FACER-AS (FACER for Android Studio); an Android Studio plugin, which uses FACER (Feature-driven API usage-based Code Examples Recommender) as its back-end code search and recommendation engine. FACER provides relevant code against natural language queries (Stage 1) and also recommends code of multiple related features (Stage 2) to facilitate opportunistic code reuse. To evaluate FACER-AS, we perform a user study involving one professional Android developer who uses our tool for the development of their ongoing live Android projects. We analyze the developer's usage of our tool over a span of seven days and find that FACER-AS achieves a 79% success rate for retrieving code against user queries (Stage 1) and a 41% success rate for recommending code for related features (Stage 2). We also observe a 43% reuse rate of Stage 1 recommendations and a 45% reuse rate of Stage 2 recommendations. Our tool's performance analysis and the developer's positive feedback show that FACER-AS can help Android developers with their coding activities. A video demonstration of our tool is available at https://youtu.be/3yN-39wP_FU and the source code of our tool is available at https://doi.org/10.5281/zenodo.5176816.

Developer communities built around software products, like the SAP Community Network, provide a knowledge base for reocurring problems and their solutions. Due to the large amount of content maintained in such communities, e.g., in forums, finding relevant solutions is a major challenge beyond the scope of common keyword-based search engines. In fact, it is measured that around 50% of the forum questions of our particular scenario have already been answered at the time they are posted. We target this challenge by an entity aware search, which exploits structured knowledge, such as domain-specific ontologies, for both query interpretation and creation of document indexes. The system takes a natural language query as input, interprets it as an entity graph, matches this graph with pre-processed content and supports the user in refining his query based on the top-k relevant entities. Results are presented in a user interface that supports faceted search based on entities. Additionally, the user interface is structured according to possible search intentions of users. The evaluation of our system on the SCN scenario yields that the top 5 entities in user queries are recognized with a precision of 83% compared to 61% of state of the art algorithms.

Motivated by the idea of reusing existing source code from previous projects within a software company, in this paper, we present a new source code recommendation technique called to help programmers find relevant implementations or sample code based on software requirement specifications. SoCeR assists programmers to search existing code repositories using natural language query. Our proposed approach summarizes Python code into sentences or phrases to match them against user queries. SoCeR extracts and analyzes the content of the code (such as variables, functions, docstrings, and comments) to generate code summary for each function which is then mapped to the respective functions. For evaluation purposes, we developed a web-based tool for users to enter a textual search query and get the relevant code search results that were most relevant to the query. In SoCeR, users can also upload new code to enrich the code base with tested code. If adopted, then SoCeR will benefit a software company to build a trusted code base enabling large-scale software code reuse.

In this paper a natural language query interface is developed for semantic and spatio-temporal querying of MPEG-7 based domain ontologies. The underlying ontology is created by attaching domain ontologies to the core Rhizomik MPEG-7 ontology. The user can pose concept, complex concept, spatial, temporal, object trajectory and directional trajectory queries. Furthermore, the system handles the negative meaning in the user query. When the user enters a natural language query, it is parsed with the link parser. According to query type, the objects, attributes, spatial relation, temporal relation, trajectory relation, time filter and time information are extracted from the parser output by using predefined information extraction rules. After the information extraction, SPARQL queries are generated, and executed against the ontology by using an RDF API. The results are used to calculate spatial, temporal, and trajectory relations between objects. The results satisfying the required relations are displayed in a tabular format and the user can navigate through the

Social scientists are increasingly interested in analyzing the semantic information (e.g., emotion) of unstructured data (e.g., Tweets), where the semantic information is not natively present. Performing this analysis in a cost-efficient manner requires using machine learning (ML) models to extract the semantic information and subsequently analyze the now structured data. However, this process remains challenging for domain experts. To demonstrate the challenges in social science analytics, we collect a dataset, QUIET-ML, of 120 real-world social science queries in natural language and their ground truth answers. Existing systems struggle with these queries since (1) they require selecting and applying ML models, and (2) more than a quarter of these queries are vague, making standard tools like natural language to SQL systems unsuited. To address these issues, we develop LEAP, an end-to-end library that answers social science queries in natural language with ML. LEAP filters vague queries to ensure that the answers are deterministic and selects from internally supported and user-defined ML functions to extend the unstructured data to structured tables with necessary annotations. LEAP further generates and executes code to respond to these natural language queries. LEAP achieves a 100% pass @ 3 and 92% pass @ 1 on QUIET-ML, with a $1.06 average end-to-end cost, of which code generation costs $0.02.