This study explores the effectiveness of layer pruning for developing more efficient BERT models tailored to specific downstream tasks in low-resource languages. Our primary objective is to evaluate whether pruned BERT models can maintain high performance while reducing model size and complexity. We experiment with several BERT variants, including MahaBERT-v2 and Google-Muril, applying different pruning strategies and comparing their performance to smaller, scratch-trained models like MahaBERT-Small and MahaBERT-Smaller. We fine-tune these models on Marathi datasets, specifically Short Headlines Classification (SHC), Long Paragraph Classification (LPC) and Long Document Classification (LDC), to assess their classification accuracy. Our findings demonstrate that pruned models, despite having fewer layers, achieve comparable performance to their fully-layered counterparts while consistently outperforming scratch-trained models of similar size. Notably, pruning layers from the middle of the model proves to be the most effective strategy, offering performance competitive with pruning from the top and bottom. However, there is no clear winner, as different pruning strategies perform better in different model and dataset combinations. Additionally, monolingual BERT models outperform multilingual ones in these experiments. This approach, which reduces computational demands, provides a faster and more efficient alternative to training smaller models from scratch, making advanced NLP models more accessible for low-resource languages without compromising classification accuracy.

In our increasingly interconnected digital world, social media platforms have emerged as powerful channels for the dissemination of hate speech and offensive content. This work delves into the domain of hate speech detection, placing specific emphasis on three low-resource Indian languages: Bengali, Assamese, and Gujarati. The challenge is framed as a text classification task, aimed at discerning whether a tweet contains offensive or non-offensive content. Leveraging the HASOC 2023 datasets, we fine-tuned pre-trained BERT and SBERT models to evaluate their effectiveness in identifying hate speech. Our findings underscore the superiority of monolingual sentence-BERT models, particularly in the Bengali language, where we achieved the highest ranking. However, the performance in Assamese and Gujarati languages signifies ongoing opportunities for enhancement. Our goal is to foster inclusive online spaces by countering hate speech proliferation.

The multilingual Sentence-BERT (SBERT) models map different languages to common representation space and are useful for cross-language similarity and mining tasks. We propose a simple yet effective approach to convert vanilla multilingual BERT models into multilingual sentence BERT models using synthetic corpus. We simply aggregate translated NLI or STS datasets of the low-resource target languages together and perform SBERT-like fine-tuning of the vanilla multilingual BERT model. We show that multilingual BERT models are inherent cross-lingual learners and this simple baseline fine-tuning approach without explicit cross-lingual training yields exceptional cross-lingual properties. We show the efficacy of our approach on 10 major Indic languages and also show the applicability of our approach to non-Indic languages German and French. Using this approach, we further present L3Cube-IndicSBERT, the first multilingual sentence representation model specifically for Indian languages Hindi, Marathi, Kannada, Telugu, Malayalam, Tamil, Gujarati, Odia, Bengali, and Punjabi. The IndicSBERT exhibits strong cross-lingual capabilities and performs significantly better than alternatives like LaBSE, LASER, and paraphrase-multilingual-mpnet-base-v2 on Indic cross-lingual and monolingual sentence similarity tasks. We also release monolingual SBERT models for each of the languages and show that IndicSBERT performs competitively with its monolingual counterparts. These models have been evaluated using embedding similarity scores and classification accuracy.

IntegriChain is the data and application backbone for market access departments of Life Sciences manufacturers. We deliver the data, the applications, and the business process infrastructure for patient access and therapy commercialization. More than 250 manufacturers rely on our ICyte Platform to orchestrate their commercial and government payer contracting, patient services, and distribution channels. ICyte is the first and only platform that unites the financial, operational, and commercial data sets required to support therapy access in the era of specialty and precision medicine. With ICyte, Life Sciences innovators can digitalize their market access operations, freeing up resources to focus on more data-driven decision support.

Our culture is defined by our values and our deep commitment to help our clients succeed. We are a division of the 38th largest company in the world and bring to bear the strength of a very large network of interconnected Hitachi companies. At the same time we remain absolutely committed to the nimble agility that helped us grow Hitachi Solutions from three founding partners to nearly 2,000 consultants, developers and support personnel all around the globe. Hitachi Solutions is a leader in providing industry solutions based on Microsoft Dynamics AX and Microsoft Dynamics CRM. Hitachi Solutions provides its customers with industry focus, software industry domain expertise, and proven tier-1 people.

At Netcentric, we come to work every day knowing we're part of the solution to the most complex challenges brands have ever faced: digital transformation. Consumer expectation of brands is increasing in a world that is more connected and fast-paced. Netcentric is a dynamic and innovative service provider with a unique culture. We empower our employees to use their creativity, looking beyond tools and technology to unlock the full potential of the Adobe Experience Cloud, so that we can deliver visionary digital marketing solutions for the world's most recognized brands. As part of the Cognizant Digital Business, we reap the benefits of combined expertise and access to multidisciplinary teams, forging ahead to become a leading customer experience player in Europe.

Avoma, Inc. is hiring for Full Time ML Engineer - NLP - Pune, Maharashtra, India - Remote - a Mid-level AI/ML/Data Science role offering benefits such as Career development, Equity, Parental leave

CloudMoyo is the partner of choice for solutions at the intersection of cloud and analytics. We help modern enterprises define their path to the Cloud and leverage the power of data driven insights. Headquartered in Bellevue, WA, with a presence in Overland Park, Kansas and an innovation center in Pune, India, CloudMoyo is set apart by the company's relentless focus on delighting customers, the strength of our smart technology accelerators, our strong business domain experience, and a deep pool of technical talent with experience in the Microsoft Cloud & Advanced Analytics.

Bigdata a buzzword itself suggest how big and voluminous your data is. To accommodate those data you require a huge storage.In recent times, big data has acquired almost every sector of the world. Even the current market trends are of Bigdata and analytics. BigData is just like an ocean in which you have many areas to learn and earn from it. Python programming is a general-purpose programming language that is open source, flexible, robust and simple.

Dr. Sachin R Sakhare is working as a Professor in the Department of Computer Engineering of Vishwakarma Institute of Information Technology, Pune, India. He has 26 Years of experience in engineering education. He is recognised as PhD guide by Savitribai Phule Pune University and currently guiding 7 PhD scholars. He is a life member of CSI, ISTE and IAEngg. He has Published 39 research communications in national, international journals and conferences, with around 248 citations and H-index 6.