Summary of Enabling Low-resource Language Retrieval: Establishing Baselines For Urdu Ms Marco, by Umer Butt et al.
Enabling Low-Resource Language Retrieval: Establishing Baselines for Urdu MS MARCO
by Umer Butt, Stalin Veranasi, Günter Neumann
First submitted to arxiv on: 17 Dec 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
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 tackles a crucial challenge in Information Retrieval (IR): creating a large-scale dataset for Urdu, a low-resource language. By translating the MS MARCO dataset through machine translation, researchers establish a baseline for zero-shot learning and then apply the mMARCO methodology to this new dataset. The results show that fine-tuning the model (Urdu-mT5-mMARCO) achieves significant improvements in Mean Reciprocal Rank (MRR@10) and Recall@10, demonstrating the potential for expanding IR access for Urdu speakers. This work highlights the importance of inclusive IR technologies and lays the groundwork for future research on language representation and South Asian languages. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about making it easier to search for information in a specific language called Urdu. Right now, there isn’t much data available for this language, which makes it hard for people who speak Urdu to find what they’re looking for online. The researchers created a big dataset of translated text to help fix this problem. They tested their approach and found that it works really well! This is important because it can help more people access information in Urdu and other languages that don’t have as much data available. |
Keywords
» Artificial intelligence » Fine tuning » Recall » Translation » Zero shot
