Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages
We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of most of the world's languages and the researchers working on these languages. Previously, unsupervised NMT, which
Garry Kuwanto +5 more
openaire +3 more sources
Survey on Data Processing and Data Augmentation in Low-resource Language Automatic Speech Recognition [PDF]
Due to the absence of transcribed speech,applying end-to-end ASR technology to low-resource language is challenging,making low-resource language ASR is a prominent research topic in NLP.Research on ASR in low-resource settings can be approached from two ...
YANG Jian, SUN Liu, ZHANG Lifang
doaj +1 more source
Clinical bacteriology in low-resource settings: today's solutions [PDF]
Low-resource settings are disproportionately burdened by infectious diseases and antimicrobial resistance. Good quality clinical bacteriology through a well functioning reference laboratory network is necessary for effective resistance control, but low ...
Ombelet, S +91 more
core +1 more source
Neural Machine Translation For Low Resource Languages
Neural Machine translation is a challenging task due to the inherent complex nature and the fluidity that natural languages bring. Nonetheless, in recent years, it has achieved state-of-the-art performance in several language pairs. Although, a lot of traction can be seen in the areas of multilingual neural machine translation (MNMT) in the recent ...
Vakul Goyle +4 more
openaire +3 more sources
Findings of the LoResMT 2020 shared task on zero-shot for low-resource languages
This paper presents the findings of the LoResMT 2020 Shared Task on zero-shot translation for low resource languages. This task was organised as part of the 3rd Workshop on Technologies for MT of Low Resource Languages (LoResMT) at AACL-IJCNLP 2020.
Ojha, Atul Kr. +3 more
core +2 more sources
Exploring the Data Efficiency of Cross-Lingual Post-Training in Pretrained Language Models
Language model pretraining is an effective method for improving the performance of downstream natural language processing tasks. Even though language modeling is unsupervised and thus collecting data for it is relatively less expensive, it is still a ...
Chanhee Lee +5 more
doaj +1 more source
The history of classics in California Community Colleges: a study of curricular shifts, 1992–2024
We present the first long-term analysis of Classics instruction in California’s community colleges, drawing on a dataset of nearly 47,000 course sections offered between 1993 and 2024.
Annie K. Lamar +3 more
doaj +1 more source
Transformers for Low-Resource Languages: Is Féidir Linn!
The Transformer model is the state-of-the-art in Machine Translation. However, in general, neural translation models often under perform on language pairs with insufficient training data. As a consequence, relatively few experiments have been carried out using this architecture on low-resource language pairs.
Lankford, Séamus +2 more
openaire +5 more sources
An HPC-Ready, Wikidata-Based Workflow for Exploratory Geocoding of Unstructured Textual Corpora
Geocoding, the task of linking place names in text to geographic coordinates, is a cornerstone of spatial humanities research, yet many existing tools assume structured data, contemporary toponyms, or commercial geocoding services that limit reuse ...
Annie K. Lamar
doaj +1 more source
The Zeno’s Paradox of ‘Low-Resource’ Languages
Accepted at EMNLP ...
Hellina Hailu Nigatu +4 more
openaire +3 more sources

