SENTENCE SENTIMENT TRANSFER USING REINFORCEMENT LEARNING WITH HUMAN FEEDBACK

This research aims to overcome the limitations of the quality of Indonesian text generation by adapting the method of reinforcement learning with human feedback (RLHF). The task carried out in this research is to use a pre-trained model to change the sentiment of positive input sentences into neg...

Full description

Saved in:
Bibliographic Details
Main Author: Ahmadetya Zaidan, Adzka
Format: Final Project
Language:Indonesia
Online Access:https://digilib.itb.ac.id/gdl/view/85070
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Institut Teknologi Bandung
Language: Indonesia