Summary of L3cube-mahanews: News-based Short Text and Long Document Classification Datasets in Marathi, by Saloni Mittal et al.
L3Cube-MahaNews: News-based Short Text and Long Document Classification Datasets in Marathi
by Saloni Mittal, Vidula Magdum, Omkar Dhekane, Sharayu Hiwarkhedkar, Raviraj Joshi
First submitted to arxiv on: 28 Apr 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 introduces L3Cube-MahaNews, a large-scale supervised Marathi text classification corpus, containing over 1.05L records classified into 12 categories. The corpus is designed for short texts, long documents, and medium paragraphs, allowing for document length-based analysis. The authors provide baseline results using state-of-the-art pre-trained BERT models, including MahaBERT, IndicBERT, and MuRIL. A comparative analysis shows that the monolingual MahaBERT model outperforms all others on every dataset. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a big database for teaching computers to classify Marathi news articles into different categories. Right now, there aren’t many examples of this in Marathi, so it’s an important step forward. The database has over 1 million examples and covers short texts, long documents, and medium-sized paragraphs. This makes it useful for studying how document length affects classification. The authors also tested some popular computer learning models on the database and found that one specifically designed for Marathi did the best job. |
Keywords
» Artificial intelligence » Bert » Classification » Supervised » Text classification
