Searcharxiv⌕ Search

arXiv subjects

Vukosi Marivate

Publications and source records attributed to Vukosi Marivate.

At least 55 records · Page 3Linked to original sources
arXiv2022

NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation

Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on. In this paper, we present NL-Augmenter, a new participatory Python-based natural language augmentation framework which supports the creation of both transformations (modifications to the data) and filters (data splits according to specific features). We describe the framework and an initial set of 117 transformations and 23 filters for a variety of natural language tasks. We demonstrate the efficacy of NL-Augmenter by using several of its transformations to analyze the robustness of popular natural language models. The infrastructure, datacards and robustness analysis results are available publicly on the NL-Augmenter repository (https://github.com/GEM-benchmark/NL-Augmenter).

cs.CL↗
arXiv2022

Semi-supervised learning approaches for predicting South African political sentiment for local government elections

This study aims to understand the South African political context by analysing the sentiments shared on Twitter during the local government elections. An emphasis on the analysis was placed on understanding the discussions led around four predominant political parties ANC, DA, EFF and ActionSA. A semi-supervised approach by means of a graph-based technique to label the vast accessible Twitter data for the classification of tweets into negative and positive sentiment was used. The tweets expressing negative sentiment were further analysed through latent topic extraction to uncover hidden topics of concern associated with each of the political parties. Our findings demonstrated that the general sentiment across South African Twitter users is negative towards all four predominant parties with the worst negative sentiment among users projected towards the current ruling party, ANC, relating to concerns cantered around corruption, incompetence and loadshedding.

cs.CL↗
arXiv2021

Training Cross-Lingual embeddings for Setswana and Sepedi

African languages still lag in the advances of Natural Language Processing techniques, one reason being the lack of representative data, having a technique that can transfer information between languages can help mitigate against the lack of data problem. This paper trains Setswana and Sepedi monolingual word vectors and uses VecMap to create cross-lingual embeddings for Setswana-Sepedi in order to do a cross-lingual transfer. Word embeddings are word vectors that represent words as continuous floating numbers where semantically similar words are mapped to nearby points in n-dimensional space. The idea of word embeddings is based on the distribution hypothesis that states, semantically similar words are distributed in similar contexts (Harris, 1954). Cross-lingual embeddings leverages monolingual embeddings by learning a shared vector space for two separately trained monolingual vectors such that words with similar meaning are represented by similar vectors. In this paper, we investigate cross-lingual embeddings for Setswana-Sepedi monolingual word vector. We use the unsupervised cross lingual embeddings in VecMap to train the Setswana-Sepedi cross-language word embeddings. We evaluate the quality of the Setswana-Sepedi cross-lingual word representation using a semantic evaluation task. For the semantic similarity task, we translated the WordSim and SimLex tasks into Setswana and Sepedi. We release this dataset as part of this work for other researchers. We evaluate the intrinsic quality of the embeddings to determine if there is improvement in the semantic representation of the word embeddings.

cs.CL↗
arXiv2021

An empirical investigation into audio pipeline approaches for classifying bird species

This paper is an investigation into aspects of an audio classification pipeline that will be appropriate for the monitoring of bird species on edges devices. These aspects include transfer learning, data augmentation and model optimization. The hope is that the resulting models will be good candidates to deploy on edge devices to monitor bird populations. Two classification approaches will be taken into consideration, one which explores the effectiveness of a traditional Deep Neural Network(DNN) and another that makes use of Convolutional layers.This study aims to contribute empirical evidence of the merits and demerits of each approach.

cs.SD↗
arXiv2021

Extracting and categorising the reactions to COVID-19 by the South African public -- A social media study

Social Media can be used to extract discussion topics during a disaster. With the COVID-19 pandemic impact on South Africa, we need to understand how the law and regulation promulgated by the government in response to the pandemic contrasts with discussion topics social media users have been engaging in. In this work, we expand on traditional media analysis by using Social Media discussions driven by or directed to South African government officials. We find topics that are similar as well as different in some cases. The findings can inform further study into social media during disaster settings in South Africa and beyond. This paper sets a framework for future analysis in understanding the opinions of the public during a pandemic and how these opinions can be distilled [in a semi-automated approach] to inform government communication in the future.

cs.SI↗
arXiv2021

Is it Fake? News Disinformation Detection on South African News Websites

Disinformation through fake news is an ongoing problem in our society and has become easily spread through social media. The most cost and time effective way to filter these large amounts of data is to use a combination of human and technical interventions to identify it. From a technical perspective, Natural Language Processing (NLP) is widely used in detecting fake news. Social media companies use NLP techniques to identify the fake news and warn their users, but fake news may still slip through undetected. It is especially a problem in more localised contexts (outside the United States of America). How do we adjust fake news detection systems to work better for local contexts such as in South Africa. In this work we investigate fake news detection on South African websites. We curate a dataset of South African fake news and then train detection models. We contrast this with using widely available fake news datasets (from mostly USA website). We also explore making the datasets more diverse by combining them and observe the differences in behaviour in writing between nations' fake news using interpretable machine learning.

cs.CL↗
arXiv2021

Towards Financial Sentiment Analysis in a South African Landscape

Sentiment analysis as a sub-field of natural language processing has received increased attention in the past decade enabling organisations to more effectively manage their reputation through online media monitoring. Many drivers impact reputation, however, this thesis focuses only the aspect of financial performance and explores the gap with regards to financial sentiment analysis in a South African context. Results showed that pre-trained sentiment analysers are least effective for this task and that traditional lexicon-based and machine learning approaches are best suited to predict financial sentiment of news articles. The evaluated methods produced accuracies of 84\%-94\%. The predicted sentiments correlated quite well with share price and highlighted the potential use of sentiment as an indicator of financial performance. A main contribution of the study was updating an existing sentiment dictionary for financial sentiment analysis. Model generalisation was less acceptable due to the limited amount of training data used. Future work includes expanding the data set to improve general usability and contribute to an open-source financial sentiment analyser for South African data.

cs.CL↗
arXiv2021

AI4D -- African Language Program

Advances in speech and language technologies enable tools such as voice-search, text-to-speech, speech recognition and machine translation. These are however only available for high resource languages like English, French or Chinese. Without foundational digital resources for African languages, which are considered low-resource in the digital context, these advanced tools remain out of reach. This work details the AI4D - African Language Program, a 3-part project that 1) incentivised the crowd-sourcing, collection and curation of language datasets through an online quantitative and qualitative challenge, 2) supported research fellows for a period of 3-4 months to create datasets annotated for NLP tasks, and 3) hosted competitive Machine Learning challenges on the basis of these datasets. Key outcomes of the work so far include 1) the creation of 9+ open source, African language datasets annotated for a variety of ML tasks, and 2) the creation of baseline models for these datasets through hosting of competitive ML challenges.

cs.CL↗
arXiv2020

Improving short text classification through global augmentation methods

We study the effect of different approaches to text augmentation. To do this we use 3 datasets that include social media and formal text in the form of news articles. Our goal is to provide insights for practitioners and researchers on making choices for augmentation for classification use cases. We observe that Word2vec-based augmentation is a viable option when one does not have access to a formal synonym model (like WordNet-based augmentation). The use of \emph{mixup} further improves performance of all text based augmentations and reduces the effects of overfitting on a tested deep learning model. Round-trip translation with a translation service proves to be harder to use due to cost and as such is less accessible for both normal and low resource use-cases.

cs.CL↗
arXiv2020

Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages

Research in NLP lacks geographic diversity, and the question of how NLP can be scaled to low-resourced languages has not yet been adequately solved. "Low-resourced"-ness is a complex problem going beyond data availability and reflects systemic problems in society. In this paper, we focus on the task of Machine Translation (MT), that plays a crucial role for information accessibility and communication worldwide. Despite immense improvements in MT over the past decade, MT is centered around a few high-resourced languages. As MT researchers cannot solve the problem of low-resourcedness alone, we propose participatory research as a means to involve all necessary agents required in the MT development process. We demonstrate the feasibility and scalability of participatory research with a case study on MT for African languages. Its implementation leads to a collection of novel translation datasets, MT benchmarks for over 30 languages, with human evaluations for a third of them, and enables participants without formal training to make a unique scientific contribution. Benchmarks, models, data, code, and evaluation results are released under https://github.com/masakhane-io/masakhane-mt.

cs.CL↗
arXiv2020

AI4D -- African Language Dataset Challenge

As language and speech technologies become more advanced, the lack of fundamental digital resources for African languages, such as data, spell checkers and Part of Speech taggers, means that the digital divide between these languages and others keeps growing. This work details the organisation of the AI4D - African Language Dataset Challenge, an effort to incentivize the creation, organization and discovery of African language datasets through a competitive challenge. We particularly encouraged the submission of annotated datasets which can be used for training task-specific supervised machine learning models.

cs.CL↗
arXiv2020

Mapping the South African health landscape in response to COVID-19

When the COVID-19 disease pandemic infiltrated the world, there was an immediate need for accurate information. As with any outbreak, the outbreak follows a clear trajectory, and subsequently, the supporting information for that outbreak needs to address the needs associated with that stage of the outbreak. At first, there was a need to inform the public of the information related to the initial situation related to the "who" of the COVID-19 disease. However, as time continued, the "where", "when" and "how to" related questions started to emerge in relation to the public healthcare system themselves. Questions surrounding the health facilities including COVID-19 hospital bed capacity, locations of designated COVID-19 facilities, and general information related to these facilities were not easily accessible to the general public. Furthermore, the available information was found to be outdated, fragmented across several platforms, and still had gaps in the data related to these facilities. To rectify this problem, a group of volunteers working on the covid19za project stepped in to assist. Each member leading a part of the project chose to focus on one of four problems related to the challenges associated with the Hospital information including: data quality, data completeness, data source validation and data visualisation capacity. As the project developed, so did the sophistication of the data, visualisation and core function of the project. The future prospects of this project relate to a Progressive Web Application that will avail this information for the public as well as healthcare workers through comprehensive mapping and data quality.

cs.CY↗
arXiv2020

Use of Available Data To Inform The COVID-19 Outbreak in South Africa: A Case Study

The coronavirus disease (COVID-19), caused by the SARS-CoV-2 virus, was declared a pandemic by the World Health Organization (WHO) in February 2020. Currently, there are no vaccines or treatments that have been approved after clinical trials. Social distancing measures, including travel bans, school closure, and quarantine applied to countries or regions are being used to limit the spread of the disease and the demand on the healthcare infrastructure. The seclusion of groups and individuals has led to limited access to accurate information. To update the public, especially in South Africa, announcements are made by the minister of health daily. These announcements narrate the confirmed COVID-19 cases and include the age, gender, and travel history of people who have tested positive for the disease. Additionally, the South African National Institute for Communicable Diseases updates a daily infographic summarising the number of tests performed, confirmed cases, mortality rate, and the regions affected. However, the age of the patient and other nuanced data regarding the transmission is only shared in the daily announcements and not on the updated infographic. To disseminate this information, the Data Science for Social Impact research group at the University of Pretoria, South Africa, has worked on curating and applying publicly available data in a way that is computer-readable so that information can be shared to the public - using both a data repository and a dashboard. Through collaborative practices, a variety of challenges related to publicly available data in South Africa came to the fore. These include shortcomings in the accessibility, integrity, and data management practices between governmental departments and the South African public. In this paper, solutions to these problems will be shared by using a publicly available data repository and dashboard as a case study.

cs.CY↗
arXiv2020

Investigating similarities and differences between South African and Sierra Leonean school outcomes using Machine Learning

Available or adequate information to inform decision making for resource allocation in support of school improvement is a critical issue globally. In this paper, we apply machine learning and education data mining techniques on education big data to identify determinants of high schools' performance in two African countries: South Africa and Sierra Leone. The research objective is to build predictors for school performance and extract the importance of different community and school-level features. We deploy interpretable metrics from machine learning approaches such as SHAP values on tree models and odds ratios of LR to extract interactions of factors that can support policy decision making. Determinants of performance vary in these two countries, hence different policy implications and resource allocation recommendations.

cs.CY↗
arXiv2020

Low resource language dataset creation, curation and classification: Setswana and Sepedi -- Extended Abstract

The recent advances in Natural Language Processing have only been a boon for well represented languages, negating research in lesser known global languages. This is in part due to the availability of curated data and research resources. One of the current challenges concerning low-resourced languages are clear guidelines on the collection, curation and preparation of datasets for different use-cases. In this work, we take on the task of creating two datasets that are focused on news headlines (i.e short text) for Setswana and Sepedi and the creation of a news topic classification task from these datasets. In this study, we document our work, propose baselines for classification, and investigate an approach on data augmentation better suited to low-resourced languages in order to improve the performance of the classifiers.

cs.CL↗
arXiv2020

Masakhane -- Machine Translation For Africa

Africa has over 2000 languages. Despite this, African languages account for a small portion of available resources and publications in Natural Language Processing (NLP). This is due to multiple factors, including: a lack of focus from government and funding, discoverability, a lack of community, sheer language complexity, difficulty in reproducing papers and no benchmarks to compare techniques. To begin to address the identified problems, MASAKHANE, an open-source, continent-wide, distributed, online research effort for machine translation for African languages, was founded. In this paper, we discuss our methodology for building the community and spurring research from the African continent, as well as outline the success of the community in terms of addressing the identified problems affecting African NLP.

cs.CL↗
arXiv2020

Investigating an approach for low resource language dataset creation, curation and classification: Setswana and Sepedi

The recent advances in Natural Language Processing have been a boon for well-represented languages in terms of available curated data and research resources. One of the challenges for low-resourced languages is clear guidelines on the collection, curation and preparation of datasets for different use-cases. In this work, we take on the task of creation of two datasets that are focused on news headlines (i.e short text) for Setswana and Sepedi and creation of a news topic classification task. We document our work and also present baselines for classification. We investigate an approach on data augmentation, better suited to low resource languages, to improve the performance of the classifiers

cs.CL↗