scholarly journals MTStemmer: A multilevel stemmer for effective word pre-processing in Marathi

2021 ◽  
Vol 12 (2) ◽  
pp. 1885-1894
Author(s):  
Virat Giri, Et. al.
Keyword(s):  
Language Processing ◽  
Performance Metrics ◽  
Main Task ◽  
Human Interactions ◽  
Processing Step ◽  
Gender Based ◽  
And Gender ◽  
Root Word ◽  
Auxiliary Verb ◽  
Modelling Process

In natural language processing, it is important that the context and the meaning of words are retained while also ensuring the efficacy of the data modelling process. During human-to-human interactions, special care is taken regarding the tense and phrasing of the words by taking into consideration the rules of grammar of the specific language. While this modification of words is necessary for framing consistent sentences, these appendages do not add significant value to the original meaning of the word. Stemming is the process of converting words back to their root form for efficient and accurate modelling of the data. In this paper, MTStemmer, a new stemmer for the Marathi language is proposed. It focuses on the stripping of suffixes for obtaining the root word form. The proposed stemmer applies a multilevel approach by taking into consideration both auxiliary verb-based suffixes and gender-based suffixes. The presented approach intends to improve upon the limitations of the previously proposed stemmers for this language. The stemming performed by the stemmer is found to be more accurate in terms of mapping to the root words. Stemming is often an important pre-processing step before processing the data further for the main task. The benefit of the proposed stemmer is demonstrated by using it for an extractive Marathi text summarization task. A significant improvement in the performance of multiple performance metrics is achieved owing to the stemming done by MTStemmer. The working of the proposed stemmer shows promising signs for the development of similar engines for other Indic languages.

scholarly journals Performance Analysis of ML Algorithms to Detect Gender Based on Voice

2021 ◽  
Author(s):  
Raz Mohammad Sahar ◽  
T. Srivinasa Rao ◽  
S. Anuradha ◽  
B. Srinivasa Rao
Keyword(s):  
Machine Learning ◽  
Performance Metrics ◽  
Point Of View ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Classification Algorithms ◽  
Gender Classification ◽  
Gender Based ◽  
And Gender

Gender classification is amongst the significant problems in the area of signal processing; previously, the problem was handled using different image classification methods, which mainly involve data extraction from a collection of images. Nevertheless, researchers over the globe have recently shown interest in gender classification using voiced features. The classification of gender goes beyond just the frequency and pitch of a human voice, according to a critical study of some of the human vocal attributes. Feature selection, which is from a technical point of view termed dimensionality reduction, is amongst the difficult problems encountered in machine learning. A similar obstacle is encountered when choosing gender particular features—which presents an analytical purpose in analyzing a human’s gender. This work will examine the effectiveness and importance of classification algorithms to the classification of gender via voice problems. Audial data, for example, pitch, frequency, etc., help in determining gender. Machine learning offers encouraging outcomes for classification problems in all domains. An area’s algorithms can be evaluated using performance metrics. This paper evaluates five different classification Algorithms of machine learning based on the classification of gender from audial data. The plan is to recognize gender using five different algorithms: Gradient Boosting, Decision Trees, Random Forest, Neural network, and Support Vector Machine. The major parameter in assessing any algorithm must be performance. Misclassifying rate ratio should not be more in classifying problems. In business markets, the location and gender of people are essentially related to AdSense. This research aims at comparing various machine learning algorithms in order to find the most suitable fitting for gender identification in audial data.

Photos from the Quarter

2020 ◽  
Vol 49 (2) ◽  
pp. 105-112
Keyword(s):  
Gender Based Violence ◽  
Gender Based ◽  
And Gender ◽  
Israeli Occupation

This sample of photos from 16 August–15 November 2019 aims to convey a sense of Palestinian life during this quarter. The images capture Palestinians across the diaspora as they fight to exercise their rights: to run for office, to vote, and to protest both Israeli occupation and gender-based violence.

THE SINS OF THE FATHER: GENDER- BASED VIOLENCE IN POST-APARTHEID SOUTH AFRICA

2017 ◽  
Vol 14 (2) ◽  
pp. 57-70 ◽  
Author(s):  
Lyn Snodgrass
Keyword(s):  
South Africa ◽  
Black Women ◽  
South African ◽  
African Women ◽  
Gender Based Violence ◽  
Political Issues ◽  
Race And Gender ◽  
Gender Based ◽  
And Gender ◽  
South African Women

This article explores the complexities of gender-based violence in post-apartheid South Africa and interrogates the socio-political issues at the intersection of class, ‘race’ and gender, which impact South African women. Gender equality is up against a powerful enemy in societies with strong patriarchal traditions such as South Africa, where women of all ‘races’ and cultures have been oppressed, exploited and kept in positions of subservience for generations. In South Africa, where sexism and racism intersect, black women as a group have suffered the major brunt of this discrimination and are at the receiving end of extreme violence. South Africa’s gender-based violence is fuelled historically by the ideologies of apartheid (racism) and patriarchy (sexism), which are symbiotically premised on systemic humiliation that devalues and debases whole groups of people and renders them inferior. It is further argued that the current neo-patriarchal backlash in South Africa foments and sustains the subjugation of women and casts them as both victims and perpetuators of pervasive patriarchal values.

Race and Gender

2020 ◽  
pp. 251-269 ◽  
Author(s):  
Timnit Gebru
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
The United States ◽  
Error Rates ◽  
Political Factors ◽  
Recidivism Rates ◽  
Race And Gender ◽  
Decision Tools ◽  
And Gender ◽  
Technical Solutions

This chapter discusses the role of race and gender in artificial intelligence (AI). The rapid permeation of AI into society has not been accompanied by a thorough investigation of the sociopolitical issues that cause certain groups of people to be harmed rather than advantaged by it. For instance, recent studies have shown that commercial automated facial analysis systems have much higher error rates for dark-skinned women, while having minimal errors on light-skinned men. Moreover, a 2016 ProPublica investigation uncovered that machine learning–based tools that assess crime recidivism rates in the United States are biased against African Americans. Other studies show that natural language–processing tools trained on news articles exhibit societal biases. While many technical solutions have been proposed to alleviate bias in machine learning systems, a holistic and multifaceted approach must be taken. This includes standardization bodies determining what types of systems can be used in which scenarios, making sure that automated decision tools are created by people from diverse backgrounds, and understanding the historical and political factors that disadvantage certain groups who are subjected to these tools.

scholarly journals Sexual health (excluding reproductive health, intimate partner violence and gender-based violence) and COVID-19: a scoping review

2021 ◽  
pp. sextrans-2020-054896
Author(s):  
Navin Kumar ◽  
Kamila Janmohamed ◽  
Kate Nyhan ◽  
Laura Forastiere ◽  
Wei-Hong Zhang ◽  
...  
Keyword(s):  
Intimate Partner Violence ◽  
Health Disparities ◽  
Reproductive Health ◽  
Sexual Health ◽  
Scoping Review ◽  
Partner Violence ◽  
Intimate Partner ◽  
Gender Based Violence ◽  
Gender Based ◽  
And Gender

ObjectivesThe COVID-19 pandemic has exposed and exacerbated existing socioeconomic and health disparities, including disparities in sexual health and well-being. While there have been several reviews published on COVID-19 and population health disparities generally—including some with attention to HIV—none has focused on sexual health (ie, STI care, female sexual health, sexual behaviour). We have conducted a scoping review focused on sexual health (excluding reproductive health (RH), intimate partner violence (IPV) and gender-based violence (GBV)) in the COVID-19 era, examining sexual behaviours and sexual health outcomes.MethodsA scoping review, compiling both peer-reviewed and grey literature, focused on sexual health (excluding RH, IPV and GBV) and COVID-19 was conducted on 15 September 2020. Multiple bibliographical databases were searched. Study selection conformed to Joanna Briggs Institute (JBI) Reviewers’ Manual 2015 Methodology for JBI Scoping Reviews. We only included English-language original studies.ResultsWe found that men who have sex with men may be moving back toward pre-pandemic levels of sexual activity, and that STI and HIV testing rates seem to have decreased. There was minimal focus on outcomes such as the economic impact on sexual health (excluding RH, IPV and GBV) and STI care, especially STI care of marginalised populations. In terms of population groups, there was limited focus on sex workers or on women, especially women’s sexual behaviour and mental health. We noticed limited use of qualitative techniques. Very few studies were in low/middle-income countries (LMICs).ConclusionsSexual health research is critical during a global infectious disease pandemic and our review of studies suggested notable research gaps. Researchers can focus efforts on LMICs and under-researched topics within sexual health and explore the use of qualitative techniques and interventions where appropriate.

Somali Immigrant Mothers’ Experiences of School Engagement: Implications for School Leaders

2021 ◽  
pp. 0013161X2110335
Author(s):  
Nimo M. Abdi
Keyword(s):  
School Engagement ◽  
School Leaders ◽  
Parental Knowledge ◽  
School Structure ◽  
Immigrant Mothers ◽  
Coloniality Of Gender ◽  
Gender Based ◽  
And Gender ◽  
Somali Immigrant ◽  
Mothers Experiences

Purpose: This critical phenomenology study examines the experiences of Somali mothers’ involvement with an urban school in London, United Kingdom. Specifically, the study explores Somali mothers’ experiences and responses in navigating the coloniality of gender discourses imbedded in school structure and culture. The research questions that guided the study concerned the gender-based tools that Somali mothers use to navigate the school structure and culture and how school leaders can recognize and tap into parental knowledge and ways of being to serve these communities. Methods: This study is based on the stories of five Somali immigrant mothers. Data collection included focus groups, field memos, site observations, and school archival data. Data were analyzed through hermeneutic interpretation of whole-part-whole. Findings: Somali mothers use three important elements—identity, resistance, and traditions—to respond to coloniality of gender in school as they negotiate tensions between the Somali conception of motherhood and western notions of gender. The findings emphasize the practices rooted in Indigenous Somali culture and gender roles as assets. Implications: This research argues that the matripotent leadership practices of Somali mothers can inform theory, practice, and policy, as these practices offer a more collective and humanizing approach to leadership centered in ideals connected to a non-Western conception of motherhood, gender, and gender dynamics.

scholarly journals Shall I Work with Them? A Knowledge Graph-Based Approach for Predicting Future Research Collaborations

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 664
Author(s):  
Nikos Kanakaris ◽  
Nikolaos Giarelis ◽  
Ilias Siachos ◽  
Nikos Karacapilidis
Keyword(s):  
Language Processing ◽  
Scientific Knowledge ◽  
Link Prediction ◽  
Performance Metrics ◽  
Future Research ◽  
Knowledge Graph ◽  
Prediction Problem ◽  
Textual Information ◽  
Research Collaborations ◽  
Processing Techniques

We consider the prediction of future research collaborations as a link prediction problem applied on a scientific knowledge graph. To the best of our knowledge, this is the first work on the prediction of future research collaborations that combines structural and textual information of a scientific knowledge graph through a purposeful integration of graph algorithms and natural language processing techniques. Our work: (i) investigates whether the integration of unstructured textual data into a single knowledge graph affects the performance of a link prediction model, (ii) studies the effect of previously proposed graph kernels based approaches on the performance of an ML model, as far as the link prediction problem is concerned, and (iii) proposes a three-phase pipeline that enables the exploitation of structural and textual information, as well as of pre-trained word embeddings. We benchmark the proposed approach against classical link prediction algorithms using accuracy, recall, and precision as our performance metrics. Finally, we empirically test our approach through various feature combinations with respect to the link prediction problem. Our experimentations with the new COVID-19 Open Research Dataset demonstrate a significant improvement of the abovementioned performance metrics in the prediction of future research collaborations.

Sign in / Sign up

Export Citation Format

Share Document