How Multilingual LLMs Can Revolutionize Education in India

February 28, 2024

India is a land of linguistic diversity, with 22 official languages and hundreds of regional and local languages spoken across the country. However, the Indian education system has not been able to fully leverage this rich resource of multilingualism, as most of the curriculum and instruction is delivered in either English (or, sometimes, Hindi), the dominant languages in the country. 

Having grown up, educated and then worked from Delhi / NCR, I have been able to avail of the benefits of both languages. Today, as we step into 2024, and after having traveled across the country, I feel that there’s a barrier for many students who are not proficient particularly in English, especially those from rural or marginalized communities, which hinders their learning outcomes and opportunities.

Fortunately, there is a new wave of innovation in the field of artificial intelligence (AI) that can potentially transform the Indian education landscape: multilingual large language models - a subset of LLMs that can handle multiple languages, either by training on a single model with data from different languages, or by using multiple models that can communicate and transfer knowledge across languages. Multilingual LLMs can enable cross-lingual understanding and generation, which can be very useful for multilingual societies like India.

But even before we discuss the multilingual LLMs from India, let’s dissect the various facets that contribute to the complexities of developing LLMs in India. 

The Challenges with the Architecture of Indian Languages

Complexities of Regional Languages

The development of Large Language Models (LLMs) for Indian languages presents a distinct challenge due to their complex grammar and cultural nuances, including idioms. Unlike English, which has a more straightforward syntax and grammar, Indian languages such as Hindi, Bengali, Telugu, Marathi, Malayalam, Gujarati, Kannada, Punjabi and Tamil have complicated sentence constructions and contextual nuances. This requires an LLM design that is not just technically advanced but also culturally sensitive.

Script Diversity and Phonetics

India's vast array of languages is also reflected in its variety of scripts, ranging from the Devanagari script of Hindi to the Gurmukhi script of Punjabi. Each of these scripts has distinct features and phonetic complexities. For a multilingual Large Language Model to be effective, it needs to be proficient in handling these diverse scripts, grasping their phonetic details.

Cultural Context and References

In India, language is intricately intertwined with cultural contexts. Idioms, regional colloquialisms, and terms laden with cultural significance play a crucial role in communication. A prime example is 'Hinglish,' a widely used blend of Hindi and English, which highlights the dynamic and intricate nature of language usage in India. It's essential for an LLM to be capable of smoothly navigating between languages, effectively capturing the nuances of such blended linguistic forms.

Other than the complexities of Indian language, the other question is of the expenses involved and the resources required.

High Training Costs and Data Scarcity

A major obstacle in creating multilingual Large Language Models for Indian languages is the lack of extensive digital data. There is a limited availability of online resources for many Indian languages, which makes gathering and organizing data both expensive and labor-intensive. Furthermore, the computational power needed to train these intricate models is considerable, resulting in higher total costs for development.

Infrastructure Questions

The scarcity of comprehensive digital data requires a strong computational framework for the training and development of models. This demands not only high-performance hardware but also advanced software tools designed to manage substantial datasets and execute complex tasks in language processing.

The good news is that a lot of regional language models are getting developed as we speak.

Examples of Multilingual LLMs for Education in India

There are several open-source multilingual LLMs that have been developed or are being developed for the Indian context, either by academic institutions, research organizations, or private companies. 


OpenHathi, developed by Sarvam AI, stands as the inaugural publicly accessible Hindi Language Model (LLM). Boasting 7 billion parameters, it adeptly handles both Hindi and English languages through a distinctive tokenizer and a three-phase training methodology. Its applications span text translation, information retrieval, and content generation, catering to the Hindi market’s diverse needs.


Tamil-LLAMA, an advanced LLM tailored for the Tamil language, is the brainchild of Abhinand Balachandran. An evolution of the LLaMA model, it significantly amplifies its capability to handle Tamil text. By integrating an additional 16,000 Tamil-specific tokens into its vocabulary, Tamil-LLAMA excels in tasks like text summarization, sentiment analysis, and text classification specific to the Tamil language.


Bhashini is a multilingual LLM that can handle 10 Indian languages, developed by Reverie Language Technologies. It has 1.5 billion parameters and can perform tasks such as text summarization, translation, and question answering, across languages. Bhashini is based on the mBERT model, but uses a novel data cleaning and filtering technique to improve its quality.

These are just some of the examples of multilingual LLMs that are built in India or for the Indian market. There are many more models that are being developed or are in the pipeline.

So, what are the benefits of these models?

Benefits of Multilingual LLMs for Education in India

Multilingual LLMs can have several benefits, such as:

Enhancing the Quality and Accessibility of Educational Content

Multilingual LLMs can help create, translate, and summarize educational content in various languages, making it more accessible and engaging for students from different linguistic backgrounds. 

For example, multilingual LLMs can help generate textbooks, lectures, quizzes, and assignments in multiple languages, or translate existing content from one language to another, or summarize long and complex content into concise and simple summaries. 

This can help students learn better and faster, as they can access content in their preferred or native language, and avoid the cognitive load of learning in a foreign language.

Enabling Personalized and Adaptive Learning

Multilingual LLMs can help provide personalized and adaptive learning experiences for students, by tailoring the content and feedback according to their individual needs, preferences, and progress. 

For instance, multilingual LLMs can help create personalized learning paths, recommend suitable learning resources, provide instant feedback, and monitor and assess the learning outcomes of students, in multiple languages. As a result, students learn at their own pace and level, and improve their motivation and retention.

Multilingual Literacy and Awareness

Multilingual LLMs can enhance multilingual literacy and awareness among students, by exposing them to diverse languages and cultures, and by encouraging them to learn and appreciate the richness and beauty of their own and other languages. 

As an example, a multilingual LLM can generate stories, poems, songs, or jokes in different languages, and explain the meaning, context, and nuances of the words and expressions used. It can also provide information and insights on the history, geography, literature, and art of different regions and communities, and inspire curiosity and creativity among students.

Empowering Teachers and Educators

Multilingual LLMs can help empower teachers and educators, by augmenting their capabilities and reducing their workload. To illustrate, multilingual LLMs can help teachers create and deliver high-quality and diverse content, provide effective and timely feedback, and evaluate and track the performance of students, in multiple languages. 

Streamlining tasks will allow teachers to concentrate on the pedagogical and emotional aspects of teaching. They can invest time in designing engaging activities, fostering discussions, and offering guidance and support without being encumbered by excessive demands.

Other than the above, multilingual LLMs can have several broader advantages that might be used for educational purposes.

Broader Opportunities in Society

Education in Rural Areas

Multilingual Large Language Models have the potential to transform education, especially in rural regions. By delivering educational materials in a range of local languages, these models can help close the gap in educational resources and enrich the learning experience.

Translation Services

Large Language Models can be crucial in offering accurate translation services, which are vital in a multilingual nation like India. They enable smooth communication between different language groups.

Upskilling and Government Digital Initiatives

In line with government efforts towards digital inclusion, Large Language Models can provide avenues for skill enhancement and expanding access to government services among speakers of various languages.

Final Words 

Overall, the opportunities look promising. By harnessing the potential of multilingual LLMs, I’m hoping that we can create a more inclusive and effective education system in India, which will cater to the needs of students from diverse backgrounds. Very soon, we may see that students from every background are competing with each other on an equal footing.

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links

This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links

Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure