Paper Title:
Encoder-Decoder Framework for Interactive Free Verses with Generation with Controllable High-Quality Rhyming
Published on:
8 May 2024
Primary Category:
Computation and Language
Paper Authors:
Tommaso Pasini,
Alejo López-Ávila,
Husam Quteineh,
Gerasimos Lampouras,
Jinhua Du,
Yubing Wang,
Ze Li,
Yusen Sun
Proposes novel fine-tuning approach for controllable, high-quality rhyming generation
Prepends rhyming word to start of each line to make critical rhyming decision first
Generates verses left-to-right for better readability compared to reverse language modeling
Extensive experiments demonstrate approach produces better rhyming and more readable text
Introduces high-quality multilingual dataset spanning 13 languages
Encoder-decoder model for interactive free verse generation with controllable high-quality rhyming
The paper proposes a novel fine-tuning approach to generate lyrics and free verse poems with controllable, high-quality rhyming. By prepending the rhyming word to the start of each line, the model makes the critical rhyming decision first while still generating the verse left-to-right. Extensive experiments show this approach produces more readable text and better rhyming compared to prior state-of-the-art methods. A high-quality multilingual dataset is also introduced to demonstrate wide applicability.
Lyrics generation from melody using language models
K-pop Lyric Translation Dataset and Analysis
Improving Large Language Model Data Generation
Instruction tuning enables controllable text generation
Simplifying and summarizing kNN language models for controllable text generation
Classifying Latin verse style with neural networks
No comments yet, be the first to start the conversation...
Sign up to comment on this paper