Rhyme-aware Chinese lyric generator based on GPT
This addresses the need for better rhyme-aware lyric generation for applications in music and poetry, but it is incremental as it builds on existing GPT models.
The paper tackled the problem of generating Chinese lyrics with poor rhyme quality by existing pre-trained language models like GPT, and the result was improved lyric generation performance through incorporating integrated rhyme information.
Neural language representation models such as GPT, pre-trained on large-scale corpora, can effectively capture rich semantic patterns from plain text and be fine-tuned to consistently improve natural language generation performance. However, existing pre-trained language models used to generate lyrics rarely consider rhyme information, which is crucial in lyrics. Using a pre-trained model directly results in poor performance. To enhance the rhyming quality of generated lyrics, we incorporate integrated rhyme information into our model, thereby improving lyric generation performance.