Summary of Conditioning Llms with Emotion in Neural Machine Translation, by Charles Brazier et al.
Conditioning LLMs with Emotion in Neural Machine Translation
by Charles Brazier, Jean-Luc Rouas
First submitted to arxiv on: 6 Aug 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
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 proposed novel MT pipeline integrates emotion information extracted from a SER model into Large Language Models (LLMs) to enhance translation quality. The approach involves fine-tuning five existing LLMs on the Libri-trans dataset and selecting the most performant model, then augmenting LLM prompts with different dimensional emotions and training the selected LLM under these configurations. Notably, integrating emotion information, particularly arousal, into LLM prompts leads to significant improvements in translation quality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers created a new way to improve machine translations by using emotional information from speech. They started by fine-tuning five different language models on a large dataset and chose the best one. Then, they added different emotions to the language model’s prompts and trained it again under these conditions. The results showed that including emotional information, especially emotions like excitement or calmness, can significantly improve translation quality. |
Keywords
» Artificial intelligence » Fine tuning » Language model » Translation
