Exploring Deep Learning Models for Lyric Generation and Addressing Biases in Word Embeddings

Abstract

The aim of this project is to explore the performance of different model architectures (such as RNN, LSTM, GRU) by generating lyrics using deep learning models, and to use the Word2Vec model for distributed semantic analysis to understand semantic phenomena and potential biases in word embedding models. The experimental results show that LSTM and GRU perform better than traditional RNN models when processing long sequence data. In addition, by analyzing word embeddings, we revealed potential gender and racial biases and proposed corresponding solutions.