Download pdf
Performance exploration of Generative Pre-trained Transformer-2 for lyrics generation
- 1 Southwest Jiaotong University
* Author to whom correspondence should be addressed.
Abstract
In recent years, the field of Natural Language Processing (NLP) has undergone a revolution, with text generation playing a key role in this transformation. This shift is not limited to technological areas but has also seamlessly penetrated creative domains, with a prime example being the generation of song lyrics. To be truly effective, generative models, like Generative Pre-trained Transformer (GPT)-2, require fine-tuning as a crucial step. This paper, utilizing the robustness of the widely-referenced Kaggle dataset titled "Song Lyrics", carefully explores the impacts of modulating three key parameters: learning rate, batch size, and sequence length. The dataset presents a compelling narrative that highlights the learning rate as the most influential determinant, directly impacting the quality and coherence of the lyrics generated. While increasing the batch size and extending sequence lengths promise enhanced model performance, it is evident that there is a saturation point beyond which further benefits are limited. Through this exploration, the paper aims to demystify the complex world of model calibration and emphasize the importance of strategic parameter selection in pursuit of lyrical excellence.
Keywords
Natural Language Processing, Lyrics Generation, Large Language Model
[1]. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., et al. (2017). Attention is all you need. Advances in neural information processing systems, 30, 1-11.
[2]. Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI blog, 1(8), 9.
[3]. Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., et al. (2020). Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 conference on empirical methods in natural language processing: system demonstrations, 38-45.
[4]. Song Lyrics, URL: https://www.kaggle.com/datasets/paultimothymooney/poetry?select=nursery_rhymes.txt. Last Accessed: 2023/09/12
[5]. Wallace, E., Feng, S., Kandpal, N., Gardner, M., & Singh, S. (2019). Universal adversarial triggers for attacking and analyzing NLP. arXiv preprint arXiv:1908.07125.
[6]. Budzianowski, P., & Vulić, I. (2019). Hello, it's GPT-2--how can I help you? towards the use of pretrained language models for task-oriented dialogue systems. arXiv preprint arXiv:1907.05774.
[7]. Xie, W., Que, M., Yang, R., Liu, C., & Yu, D. (2019). BLCU_NLP at SemEval-2019 Task 8: A Contextual Knowledge-enhanced GPT Model for Fact Checking. In Proceedings of the 13th International Workshop on Semantic Evaluation, 1132-1137.
[8]. Wu, Q., Zhang, Y., Li, Y., & Yu, Z. (2019). Alternating recurrent dialog model with large-scale pre-trained language models. arXiv preprint arXiv:1910.03756.
[9]. Mishra, P., & Sarawadekar, K. (2019). Polynomial learning rate policy with warm restart for deep neural network. In IEEE Region 10 Conference, 2087-2092.
[10]. Yang, J., & Wang, F. (2020). Auto-ensemble: An adaptive learning rate scheduling based deep learning model ensembling. IEEE Access, 8, 217499-217509.
[11]. Kochura, Y., Gordienko, Y., Taran, V., Gordienko, N., Rokovyi, A., Alienin, O., & Stirenko, S. (2020). Batch size influence on performance of graphic and tensor processing units during training and inference phases. In Advances in Computer Science for Engineering and Education II, 658-668.
[12]. Sutskever, I., Vinyals, O., & Le, Q. V. (2014). Sequence to sequence learning with neural networks. Advances in neural information processing systems, 27, 1-9.
Cite this article
Hu,Y. (2024). Performance exploration of Generative Pre-trained Transformer-2 for lyrics generation. Applied and Computational Engineering,48,53-60.
Data availability
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
Disclaimer/Publisher's Note
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.
About volume
Volume title: Proceedings of the 4th International Conference on Signal Processing and Machine Learning
© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and
conditions of the Creative Commons Attribution (CC BY) license. Authors who
publish this series agree to the following terms:
1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons
Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this
series.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published
version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial
publication in this series.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and
during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See
Open access policy for details).