Summary of Vietnamese Poem Generation & the Prospect Of Cross-language Poem-to-poem Translation, by Triet Minh Huynh and Quan Le Bao
Vietnamese Poem Generation & The Prospect Of Cross-Language Poem-To-Poem Translation
by Triet Minh Huynh, Quan Le Bao
First submitted to arxiv on: 2 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes using Large Language Models to generate Vietnamese poems from natural language prompts, allowing for enhanced content control. The most effective model, a GPT-3 Babbage variant, achieves a custom evaluation score of 0.8 in the “luc bat” genre. Additionally, the paper explores paraphrasing poems into normal text prompts and yields a high score of 0.781 in the same genre. This experiment demonstrates the potential for cross-language poem-to-poem translation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper uses big language models to create Vietnamese poems from simple texts. It’s like writing poetry, but with machines! The best model does a great job making poems that fit a certain style, and it even tries rewriting poems into regular text. This could be the start of something cool where we can translate poems between languages. |
Keywords
» Artificial intelligence » Gpt » Translation
