Summary of Multi-lingual Malaysian Embedding: Leveraging Large Language Models For Semantic Representations, by Husein Zolkepli et al.
Multi-Lingual Malaysian Embedding: Leveraging Large Language Models for Semantic Representations
by Husein Zolkepli, Aisyah Razak, Kamarul Adha, Ariff Nazhan
First submitted to arxiv on: 5 Feb 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 This paper presents a study on fine-tuning Malaysian language models, Llama2 and Mistral, for specific tasks such as semantic similarity and retrieval-augmented generation. The authors fine-tune these models on embedding tasks involving both negative and positive pairs, and release two distinct models tailored for each task. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research shows how we can improve Malaysian language models to do better at certain jobs like comparing similar words and generating text based on what we’ve already written. We took the original Llama2 and Mistral models and made them work better by training them with examples of both similar and different words. |
Keywords
* Artificial intelligence * Embedding * Fine tuning * Retrieval augmented generation
