Avancerad sökning

Visar resultat 1 - 5 av 29 uppsatser som matchar ovanstående sökkriterier.

1. 1. Bridging Language & Data : Optimizing Text-to-SQL Generation in Large Language Models

   Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

   Författare :Niklas Wretblad; Fredrik Gordh Riseby; [2024]
   Nyckelord :Chaining; Classification; Data Quality; Few-Shot Learning; Large Language Model; Machine Learning; Noise; Prompt; Prompt Engineering; SQL; Structured Query Language; Text-to-SQL; Zero-Shot Learning; Noise Identification;

   Sammanfattning : This thesis explores text-to-SQL generation using Large Language Models within a financial context, aiming to assess the efficacy of current benchmarks and techniques. The central investigation revolves around the accuracy of the BIRD-Bench benchmark and the applicability of text-to-SQL models in real-world scenarios. LÄS MER

3. 2. Few-Shot Learning for Quality Inspection

   Uppsats för yrkesexamina på avancerad nivå, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Jesper Palmér; Ahmad Alsalehy; [2023]
   Nyckelord :Few-Shot Learning; AI; Transformers; ViT Deviation; Vision Transformers;

   Sammanfattning : The goal of this project is to find a suitable Few-Shot Learning (FSL) model that can be used in a fault detection system for use in an industrial setting. A dataset of Printed Circuit Board (PCB) images has been created to train different FSL models. LÄS MER

4. 3. Evaluating and Fine-Tuning a Few-Shot Model for Transcription of Historical Ciphers

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Ingrid Eliasson; [2023]
   Nyckelord :historical ciphers; few-shot learning; automatic transcription;

   Sammanfattning : Thousands of historical ciphers, encrypted manuscripts, are stored in archives across Europe. Historical cryptology is the research field concerned with studying these manuscripts - combining the interest of humanistic fields with methods of cryptography and computational linguistics. LÄS MER

5. 4. Exploring GPT models as biomedical knowledge bases : By evaluating prompt methods for extracting information from language models pre-trained on scientific articles

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Ebba Hellberg; [2023]
   Nyckelord :Language model; GPT; knowledge probing; information extraction; prompt methods; Språkmodell; GPT; kunskapsbas; informationsextraktion; prompt-metoder;

   Sammanfattning : Scientific findings recorded in literature help continuously guide scientific advancements, but manual approaches to accessing that knowledge are insufficient due to the sheer quantity of information and data available. Although pre-trained language models are being explored for their utility as knowledge bases and structured data repositories, there is a lack of research for this application in the biomedical domain. LÄS MER

7. 5. Prompt-learning and Zero-shot Text Classification with Domain-specific Textual Data

   Master-uppsats, Uppsala universitet/Institutionen för lingvistik och filologi

   Författare :Hengyu Luo; [2023]
   Nyckelord :prompt-learning; zero-shot; few-shot; text classification; domain-specific; retail sector domain; customer-agent interaction; transformer; large language models; ChatGPT; natural language processing; machine learning; deep learning;

   Sammanfattning : The rapid growth of textual data in the digital age presents unique challenges in domain-specific text classification, particularly the scarcity of labeled data for many applications, due to expensive cost of manual labeling work. In this thesis, we explore the applicability of prompt-learning method, which is well-known for being suitable in few-shot scenarios and much less data-consuming, as an emerging alternative to traditional fine-tuning methods, for domain-specific text classification in the context of customer-agent interactions in the retail sector. LÄS MER