Summary of Persianmind: a Cross-lingual Persian-english Large Language Model, by Pedram Rostami et al.
PersianMind: A Cross-Lingual Persian-English Large Language Model
by Pedram Rostami, Ali Salemi, Mohammad Javad Dousti
First submitted to arxiv on: 12 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 introduces PersianMind, an open-source bilingual large language model that rivals closed-source GPT-3.5-turbo in the Persian language. While existing models like LLaMa are trained primarily on English datasets, resulting in poor performance in non-English languages, PersianMind leverages transfer learning to excel at transferring task knowledge from one language to another. By expanding LLaMa2’s vocabulary with 10,000 Persian tokens and training it on a dataset comprising nearly 2 billion Persian tokens, the authors demonstrate that their approach preserves the model’s English knowledge. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary PersianMind is a special kind of computer program that can understand and generate text in two languages: English and Persian. Most programs like this are designed to work well with one language but struggle with others. The new program is different because it uses something called “transfer learning” to help it understand other languages too. This means that if you train the program on a lot of Persian texts, it can get better at understanding Persian and even start to generate text in Persian itself! |
Keywords
» Artificial intelligence » Gpt » Large language model » Llama » Transfer learning
