Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 22 for “"Text-to-SQL"”.
-
Towards more robust text-to-SQL translation
… πεδίο της μετάφρασης από φυσική γλώσσα σε SQL, τα Text-to-SQL συστήματα αντιμετωπίζουν κρίσιμες προκλήσεις. Οι συλλογές δεδομένων που χρησιμοποιούνται για την εκπαίδευση και την αξιολόγηση αυτών των συστημάτων είναι ζωτικής σημασίας για τον καθορισμό της απόδοσής τους και της εξέλιξης σε …
-
Comparison and Analysis of Value Linking in Text-to-SQL systems
Τα συστήματα μετατροπής κειμένου σε SQL αντιπροσωπεύουν ένα σημαντικό βήμα προόδου στην προσβασιμότητα των δεδομένων, υποσχόμενα να δώσουν στους χρήστες τη δυνατότητα να υποβάλλουν ερωτήματα σε σύνθετες βάσεις δεδομένων χρησιμοποιώντας φυσική γλώσσα. Ωστόσο, κάτω από την επιφάνεια των εντυπωσιακών …
-
SQLyzr: A Comprehensive Benchmark and Framework for Evaluating Text-to-SQL Systems
Natural language–to–SQL (text-to-SQL) systems aim to enable users to interact with relational databases using natural language instead of SQL. Recent advances in large language models have significantly improved the performance of these systems, making them increasingly practical for real-world …
-
Error and Reliability Analysis of Open Source LLMs for Text-to-SQL Generation Across Query Complexities
… and accurately using Structured Query Language (SQL) is a crucial task in Software Engineering, but one that is time-consuming if done manually, and complicated to navigate if done through an application. However, asking a specific question about the database in natural language and using a Large …
-
Breaking the Token Barrier: Leveraging Retrieval Methods to Facilitate Text-to-SQL on Extensive Tabular Data
… is extensively utilized in the industrial sector, particularly in automotive development. This analysis is often conducted on logs generated during a system’s runtime, which typically contain sensor values, timestamps, and events. These logs represent the primary means for analyzing a system’s …
-
Towards Robust and Accurate Text-to-Code Generation
Databases play a vital role in today's digital landscape, enabling effective data storage, management, and retrieval for businesses and other organizations. However, interacting with databases often requires knowledge of query (e.g., SQL) and analysis, which can be a barrier for many users. In …
-
Towards answering unanswerable questions: data augmentation for enhanced medical domain question answering
Hospitals store patient information in relational databases known as Electronic Health Records (EHRs). Exist ing EHRs have filter and search options on the front end that are converted to SQL queries at the back end. However, these search and filter options become cumbersome when querying the EHR. …
-
Multidimensional Approaches in Bug Detection for Parallel Programming and Text-to-Code Semantic Parsing
… applies deep learning and large language models to two domains: parallel programming fault detection and text-to-code translation, aiming to enhance software reliability and natural language-driven code generation. Due to their unpredictable nature, concurrency bugs-particularly data race bugs— …
-
Statistická a genealogická analýza historických matrik s podporou jazykového modelu
… chatbota pre otázkovo-odpovedné spracovanie historických genealogických dát farnosti Frelichov. Systém kombinuje prístup Text-to-SQL pre dotazy nad relačnou databázou záznamov o približne 13\,200 osobách s prístupom Retrieval-Augmented Generation pre otázky vyžadujúce historický kontext z PDF …
-
Databázové zpracování historických matrik Frelichov a příprava datasetu pro LLM
Práce se zaměřuje na zpracování historických matričních záznamů s cílem usnadnit uživatelům jejich vyhledávání a následnou analýzu. Řešením tohoto problému je chatbot, který umožňuje konverzovat v přirozeném jazyce a generuje odpovědi založené výhradně na dostupných záznamech. Pro získání …
-
Adapting Transformers for Structured Data Domains
This research aims to enhance the adaptability and effectiveness of Transformers in structured data domains beyond their traditional use in natural language processing (NLP). We revisit key elements of the transformer framework - including input representations, attention formulations, auxiliary …
-
Learning at Test Time: Adapting Models with Synthetic Data and Environment Interaction
… models are trained before deployment, yet the context they are deployed into—the data distribution they will serve, or the environment they will act in—is often unavailable during training. This thesis studies test-time context mismatch: the setting in which information needed for reliable model …
-
Database entity recognition using language models
Natural language interfaces to databases require grounding user questions to the tables, columns, and values of a relational schema. In text-to-SQL systems this grounding is implicit, making it hard to evaluate apart from SQL generation. This thesis formalizes Database Entity Recognition (DB-ER), a …
-
Verbalising Query Results to Text
… ήδη πολύ προσπάθεια στην επίλυση 2 προβλημάτων: Text-to-SQL που επικεντρώνεται στην μετάφραση φυσικής γλώσσας σε SQL και SQL- to-Text που επιλύει το αντίστροφο πρόβλημα. Όμως, ένα πρόβλημα για το οποίο δεν έχει προταθεί λύση ακόμα είναι η εξήγηση των αποτελεσμάτων των επερωτήσεων σε φυσική …
-
Human-in-the-Loop Question Answering with Natural Language Interaction
… processing (NLP), impressive models struggle to generalize when faced with test examples that differ from the training examples: e.g., in genre, domain, or language. I study interactive methods that overcome such limitations by seeking feedback from human users to successfully complete the …
-
Deep Learning Approaches for Textual Data Generation
… the remarkable progress in image generation, textual data generation still faces many challenges and is far from perfect. This dissertation aims at addressing some key challenges in textual data generation with constraints. We focus on three topics: text-to-label generation, label-to-text …
-
Data-driven assistance for user decision making on mobile devices
Mobile devices are ubiquitous. As of 2019, two-thirds of the world population own a mobile phone. Mobile devices are indispensable for supporting billions of users' information access activities such as searching, browsing news, and shopping. Among those activities, users may often need to make …
-
Facilitating Information Access for Heterogeneous Data Across Many Languages
Information access, which enables people to identify, retrieve, and use information freely and effectively, has attracted interest from academia and industry. Systems for document retrieval and question answering have helped people access information in powerful and useful ways. Recently, natural …
-
DP-CP-RAG: DUAL-PROJECTION CONSTRAINT-PROVIDER RETRIEVAL-AUGMENTED GENERATION FOR EVIDENCE-GROUNDED PORT-DOMAIN QUESTION ANSWERING
… operational analytics requires more than plain text retrieval or direct large language model generation. In this setting, evidence is distributed across technical documents, structured operational tables, and domain-specific KPI definitions. The core challenge is not only how to retrieve …
-
Efficient Task-Oriented Dialogue State Tracking using Language Models
In the digital era, humans depend on automated systems to accomplish a wide variety of tasks that usedto require talking to a human agent, such as booking flights and hotels for their trips. This demand has driven the development of AI assistants that enable users to interact with databases and …
Page 1 of 2