scholarly journals A Little Pretraining Goes a Long Way: A Case Study on Dependency Parsing Task for Low-resource Morphologically Rich Languages

2021 ◽  
Author(s):  
Jivnesh Sandhan ◽  
Amrith Krishna ◽  
Ashim Gupta ◽  
Laxmidhar Behera ◽  
Pawan Goyal
Keyword(s):  
Dependency Parsing ◽  
Low Resource ◽  
Morphologically Rich Languages

Ties to the outside: An exploration of faculty interactions with external organizations

2018 ◽  
Vol 4 (1) ◽  
pp. 295-313 ◽  
Author(s):  
Karley A Riffe
Keyword(s):  
Study Design ◽  
Financial Constraints ◽  
Academic Discipline ◽  
Faculty Members ◽  
Faculty Work ◽  
Case Study Design ◽  
Low Resource ◽  
Faculty Interactions ◽  
Embedded Case Study

Faculty work now includes market-like behaviors that create research, teaching, and service opportunities. This study employs an embedded case study design to evaluate the extent to which faculty members interact with external organizations to mitigate financial constraints and how those relationships vary by academic discipline. The findings show a similar number of ties among faculty members in high- and low-resource disciplines, reciprocity between faculty members and external organizations, and an expanded conceptualization of faculty work.

Multi-level Chunk-based Constituent-to-Dependency Treebank Transformation for Tibetan Dependency Parsing

2021 ◽  
Vol 20 (2) ◽  
pp. 1-12
Author(s):  
Shumin Shi ◽  
Dan Luo ◽  
Xing Wu ◽  
Congjun Long ◽  
Heyan Huang
Keyword(s):  
Language Processing ◽  
Manual Annotation ◽  
Syntactic Parsing ◽  
Dependency Parsing ◽  
Low Resource ◽  
Resource Setting ◽  
Dependency Tree ◽  
Low Resource Setting ◽  
Novel Method ◽  
Multi Level

Dependency parsing is an important task for Natural Language Processing (NLP). However, a mature parser requires a large treebank for training, which is still extremely costly to create. Tibetan is a kind of extremely low-resource language for NLP, there is no available Tibetan dependency treebank, which is currently obtained by manual annotation. Furthermore, there are few related kinds of research on the construction of treebank. We propose a novel method of multi-level chunk-based syntactic parsing to complete constituent-to-dependency treebank conversion for Tibetan under scarce conditions. Our method mines more dependencies of Tibetan sentences, builds a high-quality Tibetan dependency tree corpus, and makes fuller use of the inherent laws of the language itself. We train the dependency parsing models on the dependency treebank obtained by the preliminary transformation. The model achieves 86.5% accuracy, 96% LAS, and 97.85% UAS, which exceeds the optimal results of existing conversion methods. The experimental results show that our method has the potential to use a low-resource setting, which means we not only solve the problem of scarce Tibetan dependency treebank but also avoid needless manual annotation. The method embodies the regularity of strong knowledge-guided linguistic analysis methods, which is of great significance to promote the research of Tibetan information processing.

scholarly journals Wearables beyond borders: A case study of barriers to gait assessment in low-resource settings

Maturitas ◽  
2020 ◽  
Vol 137 ◽  
pp. 7-10 ◽  
Author(s):  
A. Godfrey ◽  
C. Aranda ◽  
A. Hussain ◽  
M. Barreto ◽  
T. Rocha ◽  
...  
Keyword(s):  
Low Resource Settings ◽  
Low Resource ◽  
Gait Assessment

Analyzing Subword Techniques to Improve English to Sinhala Neural Machine Translation

2021 ◽  
pp. 2050017
Author(s):  
Rashmini Naranpanawa ◽  
Ravinga Perera ◽  
Thilakshi Fonseka ◽  
Uthayasanker Thayasivam
Keyword(s):  
Machine Translation ◽  
State Of The Art ◽  
Statistical Machine Translation ◽  
Translation System ◽  
Rare Word ◽  
Neural Machine Translation ◽  
Parallel Corpus ◽  
Low Resource ◽  
Word Level ◽  
Morphologically Rich Languages

Neural machine translation (NMT) is a remarkable approach which performs much better than the Statistical machine translation (SMT) models when there is an abundance of parallel corpus. However, vanilla NMT is primarily based upon word-level with a fixed vocabulary. Therefore, low resource morphologically rich languages such as Sinhala are mostly affected by the out of vocabulary (OOV) and Rare word problems. Recent advancements in subword techniques have opened up opportunities for low resource communities by enabling open vocabulary translation. In this paper, we extend our recently published state-of-the-art EN-SI translation system using the transformer and explore standard subword techniques on top of it to identify which subword approach has a greater effect on English Sinhala language pair. Our models demonstrate that subword segmentation strategies along with the state-of-the-art NMT can perform remarkably when translating English sentences into a rich morphology language regardless of a large parallel corpus.

scholarly journals Supporting the implementation of guidelines to prevent mother-to-child-transmission of HIV in Malawi: a multi-case study

2021 ◽  
Vol 33 (3) ◽  
pp. 178-185
Author(s):  
Chifundo Zimba ◽  
Gwen Sherwood ◽  
Barbara Mark ◽  
Jeenifer Leeman
Keyword(s):  
Contextual Factors ◽  
Interactive Systems ◽  
Dissemination And Implementation ◽  
Mother To Child Transmission ◽  
Child Transmission ◽  
Implementation Support ◽  
Low Resource ◽  
Support Strategies ◽  
Mother To Child

BackgroundHigh HIV infection and fertility rates contributed to over 12,000 children acquiring HIV from their mothers in 2011 in Malawi. To prevent mother-to-child transmission of HIV, Malawi adopted the Option B+ guidelines, and for three years, the University of North Carolina (UNC) Project provided support to strengthen guideline implementation in 134 health centres. Little is known about how implementation support strategies are delivered in low resource countries or contextual factors that may influence their delivery. The limited descriptions of support strategies and salient contextual factors limits efforts to replicate, target, and further refine strategies. Guided by the Interactive Systems Framework for Dissemination and Implementation, this study describes factors influencing implementation of support strategies and how they impacted health center staff capacity to implement Option B+ in Malawi. MethodsA qualitative multi-case study design was applied. Data were collected through site visits to 4 heath centres (2 low- and 2-high performing centres). We interviewed 18 support providers and recipients between October 2014 and October 2015. Data were analysed using content, thematic, and cross-case analysis.ResultsFour categories of strategies were used to support Option B+ guidelines implementation: training, technical assistance (TA), tools, and resources. All heath-centres implemented Option B+ guidelines for care provided between the antenatal and labor and delivery periods. Gaps in Option B+ implementation occurred during community activities and during post-delivery care, including gaps in testing of children to ascertain their HIV status at 6 weeks, 12 months, and 24 months. Salient contextual factors included staffing shortages, transportation challenges, limited space and infrastructure, limited stocks of HIV testing kits, and large patient populations.ConclusionsUnderstanding factors that influence implementation support strategies and delivery of the Option B+ guidelines, such as availability of staff and other materials/drug resources, is critical to designing effective implementation support for low resource settings.

Sign in / Sign up

Export Citation Format

Share Document