# SongNet: Rigid Formats Controlled Text Generation

arXiv: https://arxiv.org/abs/2004.08022 · HTML: https://mlsanity.com/paper/2004.08022/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Apr 2020.

## Built on by (most cited first, 26 of 26)

- [A Contrastive Framework for Neural Text Generation](https://mlsanity.com/paper/2202.06417/) (2022)
- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [Pretrained Language Models for Text Generation: A Survey](https://mlsanity.com/paper/2201.05273/) (2022)
- [DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling](https://mlsanity.com/paper/2107.01875/) (2021)
- [TeleMelody: Lyric-to-Melody Generation with a Template-Based Two-Stage Method](https://mlsanity.com/paper/2109.09617/) (2021)
- [Don't Go Far Off: An Empirical Study on Neural Poetry Translation](https://mlsanity.com/paper/2109.02972/) (2021)
- [From Tarzan to Tolkien: Controlling the Language Proficiency Level of LLMs for Content Generation](https://mlsanity.com/paper/2406.03030/) (2024)
- [ControlCap: Controllable Region-level Captioning](https://mlsanity.com/paper/2401.17910/) (2024)
- [Automatic Song Translation for Tonal Languages](https://mlsanity.com/paper/2203.13420/) (2022)
- [Songs Across Borders: Singable and Controllable Neural Lyric Translation](https://mlsanity.com/paper/2305.16816/) (2023)
- [Youling: an AI-Assisted Lyrics Creation System](https://mlsanity.com/paper/2201.06724/) (2022)
- [SongComposer: A Large Language Model for Lyric and Melody Generation in Song Composition](https://mlsanity.com/paper/2402.17645/) (2024)
- [PoetryDiffusion: Towards Joint Semantic and Metrical Manipulation in Poetry Generation](https://mlsanity.com/paper/2306.08456/) (2023)
- [Toward Unified Controllable Text Generation via Regular Expression Instruction](https://mlsanity.com/paper/2309.10447/) (2023)
- [Re-creation of Creations: A New Paradigm for Lyric-to-Melody Generation](https://mlsanity.com/paper/2208.05697/) (2022)
- [Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics](https://mlsanity.com/paper/2303.15705/) (2023)
- [Plug-and-Play Recipe Generation with Content Planning](https://mlsanity.com/paper/2212.05093/) (2022)
- [SongRewriter: A Chinese Song Rewriting System with Controllable Content and Rhyme Scheme](https://mlsanity.com/paper/2211.15037/) (2022)
- [Medical Report Generation based on Segment-Enhanced Contrastive Representation Learning](https://mlsanity.com/paper/2312.15869/) (2023)
- [Aesthetics of Sanskrit Poetry from the Perspective of Computational Linguistics: A Case Study Analysis on Siksastaka](https://mlsanity.com/paper/2308.07081/) (2023)
- [REFFLY: Melody-Constrained Lyrics Editing Model](https://mlsanity.com/paper/2409.00292/) (2024)
- [Joint Learning of Wording and Formatting for Singable Melody-to-Lyric Generation](https://mlsanity.com/paper/2307.02146/) (2023)
- [Sudowoodo: a Chinese Lyric Imitation System with Source Lyrics](https://mlsanity.com/paper/2308.04665/) (2023)
- [WakaVT: A Sequential Variational Transformer for Waka Generation](https://mlsanity.com/paper/2104.00426/) (2021)
- [Encoder-Decoder Framework for Interactive Free Verses with Generation with Controllable High-Quality Rhyming](https://mlsanity.com/paper/2405.05176/) (2024)
- [Single-Sample Decoding of a Two-Layer Sound-Word Canvas Model for Thai Klon Pad](https://mlsanity.com/paper/2610.14980/) (2026)

## Abstract (arXiv)

Neural text generation has made tremendous progress in various tasks. One common characteristic of most of the tasks is that the texts are not restricted to some rigid formats when generating. However, we may confront some special text paradigms such as Lyrics (assume the music score is given), Sonnet, SongCi (classical Chinese poetry of the Song dynasty), etc. The typical characteristics of these texts are in three folds: (1) They must comply fully with the rigid predefined formats. (2) They must obey some rhyming schemes. (3) Although they are restricted to some formats, the sentence integrity must be guaranteed. To the best of our knowledge, text generation based on the predefined rigid formats has not been well investigated. Therefore, we propose a simple and elegant framework named SongNet to tackle this problem. The backbone of the framework is a Transformer-based auto-regressive language model. Sets of symbols are tailor-designed to improve the modeling performance especially on format, rhyme, and sentence integrity. We improve the attention mechanism to impel the model to capture some future information on the format. A pre-training and fine-tuning framework is designed to further improve the generation quality. Extensive experiments conducted on two collected corpora demonstrate that our proposed framework generates significantly better results in terms of both automatic metrics and the human evaluation.