Ítem
Universitat de Girona. Departament d’Informàtica, Matemàtica Aplicada i Estadística | |
Régin, Florian
De Maria, Elisabetta Bonlaron, Alexandre |
|
3 setembre 2024 | |
Constraint Programming (CP) and Machine Learning (ML) face challenges in text generation due to CP’s struggle with implementing "meaning" and ML’s difficulty with structural constraints. This paper proposes a solution by combining both approaches and embedding a Large Language Model (LLM) in CP. The LLM handles word generation and meaning, while CP manages structural constraints. This approach builds on On-the-fly Constraint Programming Search (OTFS), improving it using LLM-generated domains. Compared to Beam Search (BS), a standard NLP method, this combined approach (OTFS with LLM) is faster and produces better results, ensuring all constraints are satisfied. This fusion of CP and ML presents new possibilities for enhancing text generation under constraints 7763.mp4 7763.mp3 |
|
audio/mpeg video/mp4 |
|
http://hdl.handle.net/10256.1/7763 | |
eng | |
Universitat de Girona. Departament d’Informàtica, Matemàtica Aplicada i Estadística | |
30th International Conference on Principles and Practice of Constraint Programming | |
Attribution-NonCommercial-ShareAlike 4.0 International | |
http://creativecommons.org/licenses/by-nc-sa/4.0/ | |
Programació per restriccions (Informàtica) -- Congressos
Constraint programming (Computer science) -- Congresses Aprenentatge automàtic -- Congressos Machine learning -- Congresses |
|
Combining Constraint Programming Reasoning with Large Language Model Predictions | |
info:eu-repo/semantics/lecture | |
DUGiMedia |