Dissertation topics suggested by the teacher.
Recent dissertations supervised by the teacher.
First cycle degree programmes dissertations
- Sviluppo di un Applicativo Web per l’Analisi dei Dati per il Teatro Comunale di Bologna
Second cycle degree programmes dissertations
- A two-step LLM-augmented distillation method for passage reranking
- Addressing Misinformation Challenges in War Scenario: Russo-Ukrainian War
- Argument Mining into Active Learning Systematic Reviews: unlocking the synergy between MARGOT and ASReview
- Automatic Terminology Coding for the Biomedical Domain
- Automating Test Case Generation for Automotive Industry using Large Language Models
- Comprehensive study of clinical entity extraction and classification using Large Language Models
- Continual Learning for Improved Trash Classification in Recycling
- Custom Data Integration for Large Language Models: Investigating Fine-tuning and Retrieval-Augmented Generation
- Design and Implementation of a Neural Machine Translation Engine for Computer-Assisted Translations
- Design and implementation of a privacy-preserving dialogue system based on argumentation
- Developing an Automated ESG Data Extraction and Analysis Tool with NLP Techniques and Large Language Models
- Developing and Comparing Machine Reasoning Models to Humans in NLP Tasks
- Diving into Song Lyrics with Large Language Models: Unveiling Metadata Insights and Fueling Video Lyrics Generation
- Efficient Information Extraction from Logistics Documents using OCR and AI Model: LayoutLMv3
- Efficient Knowledge Distillation for Green NLP Models: Bridging the Gap with Large Language Models
- Emotion Recognition for Human-Centered Conversational Agents
- Empathic Voice: Enabling Emotional Intelligence in Virtual Assistants
- Enhancing Chatbot Efficacy in Italian Language through Retrieval Augmented Generation and LoRA Fine-Tuning
- Example Sentence Suggestion for Learners of Japanese as a Second Language Using Pretrained Language Models
- Finetuning commercial Large Language Models with LoRA for enhanced Italian language understanding
- Fine-Tuning Neural Codec Language Models from Feedback with Reinforcement Learning
- From text to knowledge: Large Language Models-based methods for
knowledge extraction
- Generation of proprietary code: from the data extraction to the model finetuning and integration in multi agent system
- Generazione e valutazione di test automatici tramite modelli di NLP avanzati
- Graph Neural Networks in Recommendation Systems
- Graph-Based Keyword Extraction from Scientific Paper Abstracts using Word Embeddings
- Hierarchical Multi-Label Text Classification in a Low-Resource Setting
- Intermediate linguistic task fine-tuning on Multi-lingual models
- Knowledge graph embedding enhancement using ontological knowledge in the biomedical domain
- Leveraging Large Language Models for Content Analysis and Generation for Podcast Transcriptions
- Neural Clustering on Tree Structured Data: A case study on Argument Mining
- Neural-Symbolic Learning: challenges and benchmarks
- On the use of Prompting for Fine-Tuning Neural models for Speech Processing
- Prompting techniques for Natural Language Generation in the Medical Domain
- Quality and Aspect based Argument Generation
- Realizzazione di uno slave EtherCAT integrante periferiche per applicazioni motion control
- Royalty-Management Smart Contracts with Graph Neural Network-based Artist Recommendations
- SynBA: A contextualized Synonim-Based adversarial Attack for text classification
- Text Style Transfer in Italian Newspaper Articles
- Time Sensitive Networking: implementation of a Real Time communication protocol for Machine to Machine and Controller to Controller communication in a Real Time environment
- Tree regularized neural networks for key point analysis
- Unstructured Knowledge Integration with Annotation Guidelines: A case study on text classification
- Vocabulary Transfer and Knowledge Distillation for Language Model Compression
- Voice Cloning: Increasing Expressivity of Italian Text-to-Speech with Phonemization
- Voice conversion with pre-trained representations for audio anonymization