Doing cool things with data — Introduction Grammatical Error Correction (GEC) systems aim to correct grammatical mistakes in the text. Grammarly is an example of such a grammar correction product. Error correction can improve the quality of written text in emails, blog post, and chats. The GEC task can be thought of as a sequence to sequence…

Doing cool things with Data! — Introduction Recent advances in large language models (LLMs) like GPT-4 have shown impressive capabilities in generating coherent text. However, parsing and understanding research papers accurately remains an extremely challenging task for AI. Research papers contain complex formatting, math equations, tables, figures, and domain-specific language. The density of information is very high…

Doing cool things with data! Introduction As a developer, efficiently navigating large codebases can be a headache. When working with extensive GitHub repositories containing many interconnected files and functions, finding the specific snippet you need often feels like searching for a needle in a haystack. In this post, I explore building…

Doing cool things with data — Introduction In the era of big data and advanced artificial intelligence, language models have emerged as formidable tools capable of processing and generating human-like text. Large Language Models like ChatGPT are general-purpose bots capable of having conversations on many topics. However, LLMs can also be fine-tuned on domain-specific data making them…

Doing cool things with data Introduction Climate change is poised to be the biggest crisis of our generation. The environmental degradation from Greenhouse Gases (GHG) will result in significant challenges ranging from more frequent disasters and their associated economic costs to more diseases due to a warmer planet and food and…

Doing cool things with data! Introduction This blog discusses the translation of a French history article into English followed by a summarization of that article in English. We show how pre-trained models can be used to do this very quickly. …

Doing cool things with data — Introduction Question Answering is a popular application of NLP. Transformer models trained on big datasets have dramatically improved the state-of-the-art results on Question Answering. The question answering task can be formulated in many ways. The most common application is an extractive question answering on a small context. The SQuAD dataset is…

Doing cool things with data — Introduction 3D computer vision is a fascinating field teaching model to understand the world as we do. A tremendous amount of progress has been made recently on 2D computer vision tasks involving object detection, segmentation, keypoint estimation etc. …

Doing cool things with data — Introduction NLP is going to be the most transformational tech of this decade. And Transformer models are fuelling the advancement in NLP. In this blog, we look at an application of Transformers on multilingual data. Many businesses are now global in their reach and are collecting data in many languages. NLP…