L3cube-hindbert and devbert: Pre-trained bert transformer models for devanagari based hindi and marathi languages
R Joshi - arXiv preprint arXiv:2211.11418, 2022 - arxiv.org
The monolingual Hindi BERT models currently available on the model hub do not perform
better than the multi-lingual models on downstream tasks. We present L3Cube-HindBERT, a …
better than the multi-lingual models on downstream tasks. We present L3Cube-HindBERT, a …
L3cube-mahacorpus and mahabert: Marathi monolingual corpus, marathi bert language models, and resources
R Joshi - arXiv preprint arXiv:2202.01159, 2022 - arxiv.org
We present L3Cube-MahaCorpus a Marathi monolingual data set scraped from different
internet sources. We expand the existing Marathi monolingual corpus with 24.8 M sentences …
internet sources. We expand the existing Marathi monolingual corpus with 24.8 M sentences …
Mono vs multilingual bert for hate speech detection and text classification: A case study in marathi
A Velankar, H Patil, R Joshi - IAPR Workshop on Artificial Neural Networks …, 2022 - Springer
Transformers are the most eminent architectures used for a vast range of Natural Language
Processing tasks. These models are pre-trained over a large text corpus and are meant to …
Processing tasks. These models are pre-trained over a large text corpus and are meant to …
Hate and offensive speech detection in hindi and marathi
A Velankar, H Patil, A Gore, S Salunke… - arXiv preprint arXiv …, 2021 - arxiv.org
Sentiment analysis is the most basic NLP task to determine the polarity of text data. There
has been a significant amount of work in the area of multilingual text as well. Still hate and …
has been a significant amount of work in the area of multilingual text as well. Still hate and …
L3cube-mahahate: A tweet-based marathi hate speech detection dataset and bert models
A Velankar, H Patil, A Gore, S Salunke… - arXiv preprint arXiv …, 2022 - arxiv.org
Social media platforms are used by a large number of people prominently to express their
thoughts and opinions. However, these platforms have contributed to a substantial amount …
thoughts and opinions. However, these platforms have contributed to a substantial amount …
An unsupervised annotation of Arabic texts using multi-label topic modeling and genetic algorithm
HA Almuzaini, AM Azmi - Expert Systems with Applications, 2022 - Elsevier
Every day the world produces an enormous amount of textual data. This unstructured text is
of little use unless it is labeled using a combination of categories, keywords, tags. Humans …
of little use unless it is labeled using a combination of categories, keywords, tags. Humans …
L3cube-mahanlp: Marathi natural language processing datasets, models, and library
R Joshi - arXiv preprint arXiv:2205.14728, 2022 - arxiv.org
Despite being the third most popular language in India, the Marathi language lacks useful
NLP resources. Moreover, popular NLP libraries do not have support for the Marathi …
NLP resources. Moreover, popular NLP libraries do not have support for the Marathi …
Comparative study of long document classification
V Wagh, S Khandve, I Joshi, A Wani… - TENCON 2021-2021 …, 2021 - ieeexplore.ieee.org
The amount of information stored in the form of documents on the internet has been
increasing rapidly. Thus it has become a necessity to organize and maintain these …
increasing rapidly. Thus it has become a necessity to organize and maintain these …
A survey on NLP resources, tools, and techniques for Marathi language processing
Natural Language Processing (NLP) has been in practice for the past couple of decades,
and extensive work has been done for the Western languages, particularly the English …
and extensive work has been done for the Western languages, particularly the English …
L3cube-mahaner: A marathi named entity recognition dataset and bert models
Abstract Named Entity Recognition (NER) is a basic NLP task and finds major applications
in conversational and search systems. It helps us identify key entities in a sentence used for …
in conversational and search systems. It helps us identify key entities in a sentence used for …