Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Dense Retrieval for Low Resource Languages -- the Case of Amharic Language

Domain:

natural language processing

Record type:

paperdataset
Creator:
YesGarMolMot
Host:avatar
This paper reports some difficulties and some results when using dense retrievers on Amharic, one of the low-resource languages spoken by 120 millions populations. The efforts put and difficulties faced by University Addis Ababa toward Amharic Information Retrieval will be developed during the presentation. 4 pages, 2 figures

Visit

arxiv.org

Tasks

information retrieval

Languages

Amharic

Tags

Information RetrievalComputation and Language

Similar

samyakjain20/Dense-Retrieval-for-Low-Resource-LanguageQuery Augmentation for Cross-Lingual Dense Retrieval in Low-Resource LanguagesWhat are the limits of cross-lingual dense passage retrieval for low-resource languages?Synthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource LanguagesDiversity in Training Languages for Dense Retrieval and Zero-Shot Accuracy in Low-Resource BenchmarksComparative Analysis of Hybrid Batch and Standard Multilingual Dense Retrieval on MIRACL for Low-Resource Languages

samyakjain20/Dense-Retrieval-for-Low-Resource-Language

Built a specialized query answering retrieval model designed for low-resource languages. Utilized da

Query Augmentation for Cross-Lingual Dense Retrieval in Low-Resource Languages

Effective cross-lingual dense retrieval methods that rely on multilingual pre-trained language model

What are the limits of cross-lingual dense passage retrieval for low-resource languages?

In this paper, we analyze the capabilities of the multi-lingual Dense Passage Retriever (mDPR) for e

Synthetic Query Augmentation for Zero-Shot Cross-Lingual Dense Retrieval in Low-Resource Languages

Multilingual Pretrained Language Models (MPLMs) perform strongly in cross-lingual transfer. We propo

Diversity in Training Languages for Dense Retrieval and Zero-Shot Accuracy in Low-Resource Benchmarks

Accuracy of English-language Question Answering (QA) systems has improved significantly in recent ye

Comparative Analysis of Hybrid Batch and Standard Multilingual Dense Retrieval on MIRACL for Low-Resource Languages

Information retrieval across different languages is an increasingly important challenge in natural l