Dravidian Languages Research Articles

Old Scriptural Monuments of Dravidam

In terms of language history, the Tamil literature in power today takes us to the second (a) third century AD, but the Dravidian words given by the Greek authors take us beyond the pre-Christian era. The oldest monuments of the Dravidian language are the vocabularies given by the Greek authors. The Dravidian languages have been excellent for two thousand years without any deterioration. All the words mentioned in this article must have been used in ancient times. Language is divided. After the arrival of the Aryans at the time when the Dravidian people started to live there, various languages were mixed in the Aryan period which is their common possession today. This article makes it clear that all the words are there.

Arivumathi and Dravidianism

Superstitions, rituals, religion, and godly principles that arose from the emergence of the Dravidian movement and the rise of the Dravidian race are enslaving the people. It was through this that those human beings created ups and downs among themselves and locked up the slave animals for themselves. Untouchability was an act of demeaning a man. This atrocity of untouchability was seen in restaurants, art halls, buses, and even schools, with separate cups, separate seats, and separate sections. In addition to demeaning women, there were many oppressive policies in Tamil Nadu, such as that a woman is a slave to a man, home, and society. The Dravidian movement was a movement that emerged to rescue the people from many more such forms of oppression. Even Tamil, the oldest language of the Dravidian languages, began to lose its uniqueness at some point. In order to bring the Tamil language out of this decline, the speakers of the Dravidian movement like Thanthai Periyar, Anna, and Kalaignar promoted Tamil through their self-conscious speeches. Similarly, many poets of the Dravidian movement, like Bharathidasan, Suradha, Vanithasan, etc., through their writings, worked hard to make the Tamil language flourish on our soil again. Arivumathi is one of those who have been attracted by such principles and who is now a poet of the Dravidian movement. The Dravidian thoughts found in his poems can be seen in poems such as his unique Tamil principles, his attachment to race, the restoration of slavery, and his concept of untouchability.

Dravidian Aesthetics - the foremost of Indian Aesthetics

The influences of contemporary events on the field of study and society on speakers of Dravidian languages such as Tamil indicate the primacy of Dravidian ideology. Scholars in other countries look at the functioning of the Dravidian movement in the political, social, and cultural spheres behind the Tamil aesthetics of Dravidian aesthetics being at the forefront of Indian aesthetics. The Czechoslovakian multi-linguist recalls in the interview the Sanskrit-Tamil linguistic exchanges, the unity, and other differences. The contribution of Dravidian culture to Indianization is revealed through the media interviews of Sri Lankan Tamil scholar Karthikesu Sivathambi. There is an explanation of the understanding of Tamil consciousness. Accordingly, the Dravidian movement developed by rejecting the Sanskrit tradition, the North Indian tradition, the Bhakti tradition, etc. Aside from religion, which is a feature of the past, the temple towers, the Nataraja image, the bhakti literature, etc., must be regarded as the active contribution of the Tamils, who were fully absorbed in Indian culture. These aspects were not adopted because of the atheistic, rationalist, and anti-Brahmin elements of the Dravidian movement. BC 100- AD 250 lays claim to Sangam literature, the Pre-Bhakti period literature. The central theme of the article was that the Dravidian movement regarded it as belonging to Tamils who did not have the Sanskrit tradition. It is understood that the contributions of Periyar and others led to the development of the Dravidian cultural ideology. Experts in other languages expound on Dravidian aesthetics. Malayalam scholar K. Ayyappa Panicker praises the Thinai doctrine of Tamil as a rare wealth of knowledge not found in the languages of the world. Not all Sanskrit language texts are based on the orthodox tradition they also include books.

Seeing into the Mind in Early Modern South India

In contrast to the many South Asian texts that explore deep, metaphysically oriented states of mind, introspection of a personal, empirical, everyday kind is relatively rare in the textual archive until the early modern period, beginning roughly in the 16th century. At that time a remarkable richness of personal introspective works is evident in all the major south Indian languages. This article explores some of the features of that literature, with representative examples of literary, musical, and philosophical sources focused on the individual and on her or his sense of self.

Kavi-Kannada Natural Language Processing System

Southwest Indian state of Karnataka is home to the majority of speakers of the ancient Dravidian language known as Kannada. The word models embeddings are employed in natural language processing for upcoming Indic NLP work. We convert Kannada voice data to Kannada text data using machine learning techniques and a specific analogy and similarity challenge, and then access our models for the subsequent task of text classification.

Social Thinker Iyothee Thass Pandithar

Iyothee Thass Was South India’s first anti-caste militant, social worker, Tamil scholar and psychiatrist. He was one of the pioneers in the formation of Dravidian movement. He was active in the fields of politics, religion and literature for the betterment of the oppressed people. He advised Buddhism that the original religion of the Pariyars was Buddhism and therefore they should convert to Buddhism. Apart from Tamil, he is proficient is Sanskrit, Pali and English. Iyothee Thass, who throughout his life worked for the interests of the oppressed, was one of the foremost proponents of the Dravidian and ‘Tamil’ identities. He coined the term ‘Dravidian’ as a political term that was only used by those who were engaged in research on the Dravidian language family. Iyothee Thass is an astonishing researcher. It is time to strictly follow the practice of untouchability of caste on Dalit people. He was a pioneer for Periyar at the Tamil Nadu level and Ambedkar at the Indian level for policies such as rational reservation, social change, caste eradication and anti-Hinduism in higher caste iyothe Thass Pandit was the first create such a social change

Multilingual hope speech detection in English and Dravidian languages

Recent work on language technology has aimed to identify negative language such as hate speech and cyberbullying as well as improve offensive language detection to mediate social media platforms. Most of these systems rely on using machine learning models along with the labelled dataset. Such models have succeeded in identifying negativity and removing it from the platform deleting it. However, recently, more research has been conducted on the improvement of freedom of speech on social media. Instead of deleting supposedly offensive speech, we developed a multilingual dataset to identify hope speech in the comments and promote positivity. This paper presents a multilingual hope speech dataset that promotes equality, diversity and inclusion (EDI) in English, Tamil, Malayalam and Kannada. It was collected to promote positivity and ensure EDI in language technology. Our dataset is unique, as it contains data collected from the LGBTQIA+ community, persons with disabilities and women in science, engineering, technology and management (STEM). We also report our benchmark system results in various machine learning models. We experimented on the Hope Speech dataset for Equality, Diversity and Inclusion (HopeEDI) using different state-of-the-art machine learning models and deep learning models to create benchmark systems.

Rice and Water in Early Historic South India and Sri Lanka

Domesticated rice (Oryza sativa), typically a water-intensive crop, is widely cultivated in the semi-arid zones of South India and Sri Lanka and is a staple among sedentary populations in these regions when the opposite should prevail in light of environmental constraints. This paper investigates the origins of large-scale rice cultivation in South India and Sri Lanka and the attendant innovations in hydraulic technologies using a wide range of sources but with a special focus on Tamil ”Caṅkam” texts, the earliest surviving textual corpus for the Dravidian language family.

'Nilam Poothu Malarntha Nal' Naavalil Arasa Vazhvum Paanar Edapeyarchiyum

The man who lived a nomadic life in the early days of the world established his abode in rich areas and established a stable life. Through his exchange of thoughts and ideas many literatures appeared in the settled areas. Literary exchanges took place in Tamil and Malayalam, which are considered to be the twin children of the Dravidian languages. In that way, there has been a need to explore the displacement elements of Panar and Pulavar life through Manojkurur’s Nilam Poothu Malarntha Naal, a novel written in Malayalam in modern times, focusing on Sangam literature which proclaims the antiquity of Tamil. The hardships that occur when Panars go from town to town to see the kings, the disparity between the Panars and the poets, the lifestyles of the Panars community, and the political background are the reasons for the migration.

Offence Detection in Dravidian Languages Using Code-Mixing Index-Based Focal Loss

Offence Detection in Dravidian Languages Using Code-Mixing Index-Based Focal Loss

‘Anâshir al-Jumal baina al-Lughataini al-‘Arabiyyah wa at-Tâmiliyyah (Dirâsâh Taqâbuliyyah)

Each language has a specific pattern in sentence structure. Based on this, sentence pattern in Arabic language differs from Tamil language since they are from two different linguistic families namely Semitic language family and Dravidian language family respectively. Therefore, this research focuses on studying sentence pattern in Arabic and Tamil languages by exposing similarities and dissimilarities between them. This research uses contrastive descriptive methodology. This research finds that there are more dissimilarities than similarities in sentence pattern between Arabic and Tamil languages whence use of gender, number, tense, adjective, genitive and articles. As for the similarities, they are in sentence elements, nominal sentence and interrogative sentence.

Multi-task learning in under-resourced Dravidian languages

It is challenging to obtain extensive annotated data for under-resourced languages, so we investigate whether it is beneficial to train models using multi-task learning. Sentiment analysis and offensive language identification share similar discourse properties. The selection of these tasks is motivated by the lack of large labelled data for user-generated code-mixed datasets. This paper works with code-mixed YouTube comments for Tamil, Malayalam, and Kannada languages. Our framework is applicable to other sequence classification problems irrespective to the size of the datasets. Experiments show that our multi-task learning model can achieve high results compared to single-task learning while reducing the time and space constraints required to train the models on individual tasks. Analysis of fine-tuned models indicates the preference of multi-task learning over single task learning resulting in a higher weighted F1 score on all three languages. We apply two multi-task learning approaches to three Dravidian languages, Kannada, Malayalam, and Tamil. Maximum scores on Kannada and Malayalam were achieved by mBERT subjected to cross entropy loss and with an approach of hard parameter sharing. Best scores on Tamil was achieved by DistilBERT subjected to cross entropy loss with soft parameter sharing as the architecture type. For the tasks of sentiment analysis and offensive language identification, the best performing model scored a weighted F1-Score of (66.8%, 90.5%), (59%, 70%) and (62.1%,75.3%) for Kannada, Malayalam and Tamil on sentiment analysis and offensive language identification respectively.

Characteristics of Telugu in Middle Dravidian Languages

Telugu language can be mentioned next to tamil in terms of antiquity and pronuncication. Telugu is spoken in andhra pradesh and place like south africa in our indian country telugu is the second most widely spoken language after hindi. It is a literary language like tamil. Those who study the reson for the name o this language will think in various ways that the word thrillingam was changed to telugu and it is also believed that the word ‘Tenuge’ which meens sweetness was given knowing that it was telugu. Many grammars have been written in the language from the western country. Northern Scholars, such as nannayapattar have written a number of literatures in this language. The language, which is spoken by more people than tamil is thriving with a variety of creativity. In terms of gender discrimination, telugu can be seen to be different from other dravidian languages the sound and writing script of the telugu language are considered to be the most excellent. The people of chennai who migrated to places like sumatra and java are considered as telugus. That is why the telugu language is still existing as very prominent today.

Individual Theory of Tholkappiyam

There are many ancient language families in the world. Among them, the Dravidian language family is considered essential. The grammatical system and its trends have changed at various stages in the grammar composed in Tamil among the other languages. Grammar is about explaining those rules. The concept of individual theory develops by interpreting the structure of a language with structural order, using a specific grammatical theoretical concept for a given language over a period of time. Individualism does not operate in the context of any language, but it can construct the grammar of a language written over a period of time. The concepts of grammar are written under the categories such as, summation, type, extension, genealogy, etc., by using social, political, and academic problems to present individual theory. The interpretation of the structural order of language as a separate text without a linguistic background is consistent with the concept of individualism.

A Dedicated Sarcasm Construction in Kashmiri as a Feature of the South Asian Linguistic Area

This paper has two parts. In the first part (§§ 2‑3) we cover some of the resources that the Kashmiri sarcast draws on. In the second part (§§ 4‑6) we explore a particular formulaic construction that we maintain is specifically dedicated to the expression of sarcasm, not only in Kashmiri but in most languages of the Indo‑Aryan family – with the possible exception of Bangla and its neighbours. Since this construction occurs in some but not all the major Dravidian languages, it may be regarded as another feature or ‘trait’ of the South Asian Linguistic Area first adumbrated by Emeneau (1956) and further extended by Masica (1976).

Post-focus compression in Brahvi and Balochi.

Previous research has shown that post-focus compression (PFC)- the reduction of pitch range and intensity after a focused word in an utterance, is a robust means of marking focus, but it is present only in some languages. The presence of PFC appears to follow language family lines. The present study is a further exploration of the distribution of PFC by investigating Brahvi, a Dravidian language, and Balochi, an Indo-Iranian language. Balochi is predicted to show PFC given its presence in other Iranian languages. Dravidian languages have not been studied for prosodic focus before and they are not related to any languages with PFC. We recorded twenty native speakers from each language producing declarative sentences in different focus conditions. Acoustic analyses showed that,in both languages, post-focus f0 and other correlates were significantly reduced relative to baseline neutral-focus sentences, but post-focus lowering of f0, and intensity was greater in magnitude in Balochi than in Brahvi. The Balochi results confirm our prediction, while the Brahvi results offer the first evidence ofPFC in a Dravidian language. The finding of PFC in a Dravidian language is relevant to a postulated origin of PFC, which is related to the controversial Nostratic Macrofamily hypothesis.

Hate speech and offensive language detection in Dravidian languages using deep ensemble framework

Social networking platforms gained widespread popularity and are used for various activities like: promoting products, sharing news, achievements and many more. On the other hand, it is also used for spreading rumors, bullying people, and abusing certain groups of people with hateful words. The hate and offensive posts must be detected and removed as early as possible from the social platforms because such posts are spread very quickly and tend to have a lot of negative impacts on human beings. In the last few years, offensive content and hate speech detection has become popular topic of research. Detecting hate speech on social platforms has many challenges, one of them being the use of code-mixed language. Majority of the social media users usually post their messages in code-mixed languages such as Hindi–English, Tamil–English, Malayalam–English, Telugu–English and others. In this exhaustive study, we explore and compare the use of various machine learning and deep learning approaches. An ensemble model by combining the outcomes of transformer and deep learning-based models is suggested to detect hate speech and offensive language on social networking platforms. The experimental outcomes of the proposed weighted ensemble framework outperformed state-of-the-art models by achieving 0.802 and 0.933 weighted F1-score for Malayalam and Tamil code-mixed datasets.

Comparison and Validation of Acoustic Voice Quality Index Version 2 and Version 3 among South Indian Population

Acoustic Voice Quality Index (AVQI) has emerged in the recent past as a robust multiparametric voice quality evaluation tool. Two versions of AVQI derived using the program PRAAT have found extensive clinical and research applications. These versions have been validated in several languages around the world. However, no research reports are available on validation of AVQI in the South Indian population. Further, studies comparing the performance of the two versions of AVQI are limited in the literature. This study was designed to validate and compare the two versions of AVQI (AVQIv02.02 and AVQIv03.01) in South Indian languages (Malayalam and Kannada). A retrospective analysis of previously recorded voice samples was carried out on a total of 160 (91 normophonic and 69 dysphonic) voice samples. These samples were perceptually rated on a GRBAS scale by five experienced speech-language pathologists. Standardized Syllable Number (SSN) necessary to derive AVQIv03.01 was computed. Following this, these samples were analyzed to obtain the AVQIv02.02 and AVQIv03.01. The concurrent validity and diagnostic accuracy of these measures were then examined and compared. A moderate agreement was obtained across the judges on perceptual evaluation of voice quality. SSN in Malayalam and Kannada languages were identified to be 29 and 25 syllables respectively. Language differences were not observed on both versions of AVQI. The concurrent validity of AVQIv03.01 (r = 0.788) was superior to that of AVQIv02.02 (r = 0.655). Further, the threshold of differentiating normophonic and dysphonic samples were determined to be >3.45 for AVQIv02.02 and >2.45 for AVQIv03.01. AVQIv03.01 is superior to AVQIv02.02 in terms of its diagnostic accuracy and concurrent validity. Current findings also extend the application of AVQI as a robust tool for the evaluation of voice characteristics to the South Indian population.

DravidianCodeMix: sentiment analysis and offensive language identification dataset for Dravidian languages in code-mixed text

This paper describes the development of a multilingual, manually annotated dataset for three under-resourced Dravidian languages generated from social media comments. The dataset was annotated for sentiment analysis and offensive language identification for a total of more than 60,000 YouTube comments. The dataset consists of around 44,000 comments in Tamil-English, around 7000 comments in Kannada-English, and around 20,000 comments in Malayalam-English. The data was manually annotated by volunteer annotators and has a high inter-annotator agreement in Krippendorff’s alpha. The dataset contains all types of code-mixing phenomena since it comprises user-generated content from a multilingual country. We also present baseline experiments to establish benchmarks on the dataset using machine learning and deep learning methods. The dataset is available on Github and Zenodo.

Text-to-Speech Synthesis: Literature Review with an Emphasis on Malayalam Language

Text-to-Speech Synthesis (TTS) is an active area of research to generate synthetic speech from underlying text. The identified syllables are uttered with proper duration and prosody characteristics to emulate natural speech. It falls under the category of Natural Language Processing (NLP), which aims to bridge the gap in communication between human and machine. So far as Western languages like English are concerned, the research to produce intelligent and natural synthetic speech has advanced considerably. But in a multilingual state like India, many regional languages viz. Malayalam is underexplored when it comes to NLP. In this article, we try to amalgamate the major research works performed in the area of TTS in English and the prominent Indian languages, with a special emphasis on the South Indian language, Malayalam. This review intends to provide right direction to the research activities in the language, in the area of TTS.