Summary of Non-contextual Bert or Fasttext? a Comparative Analysis, by Abhay Shanbhag et al.
Non-Contextual BERT or FastText? A Comparative Analysis
by Abhay Shanbhag, Suramya Jadhav, Amogh Thakurdesai, Ridhima Sinare, Raviraj Joshi
First submitted to arxiv on: 26 Nov 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 paper investigates the effectiveness of non-contextual BERT embeddings in Natural Language Processing (NLP) tasks for low-resource languages like Marathi. It focuses on MuRIL and MahaBERT models, as well as FastText models IndicFT and MahaFT, to analyze their performance in news classification, sentiment analysis, and hate speech detection. The results show that non-contextual BERT embeddings extracted from the first layer outperform FastText embeddings, offering a promising alternative for low-resource NLP tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how well non-BERT language processing works for languages with limited data and resources. It uses special word representations called embeddings to help machines understand words in these languages. The study compares different types of embeddings from BERT models like MuRIL and MahaBERT, as well as FastText models IndicFT and MahaFT, to see which ones work best for tasks like classifying news, understanding emotions, and detecting hate speech. |
Keywords
» Artificial intelligence » Bert » Classification » Fasttext » Natural language processing » Nlp
