Natural Language Processing

Author : Indrajit Singh Submitted on : 5 Dec 2020 Abstract – Search has never been so easy and there has been always a gap between what a user needs and what the search engine returns as an output. In today’s world we tend to search everything in google without thinking much about the results. […]

Introduction Moving up the value chain CellStrat would like to encourage discussions and webinars focusing on the application of AI in Real Life problem-solving. A beginning has already been made and this is another step in that direction. The use of Deep Learning and Reinforcement Learning to solve a complex Strategic Negotiation is a very […]

Survey forms, invoices, bills, memos, tenders, and myriad such documents which businesses face on daily basis. These are full of numbers, characters, images, signatures etc…in almost all languages worldwide…. hard to imagine our world without any languages. Think about how many text and voice data we face every day. What about determining meaning from this […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Last Saturday, AI Researcher Indrajit Singh presented a marvellous workshop on “Bidirectional Encoder Representations from Transformers” – also called “BERT” in short. We are in the era of Pre-trained models in AI. The figure below shows tons of pre-trained models which have taken root. BERT is one of the core models […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #WhereLearningNeverStops Last Saturday, our AI Lab Researcher Indrajit Singh presented an exhaustive webinar on Transformers, which are used in NLP. Introduction To combine the advantages from both CNNs and RNNs, [Vaswani et al., 2017] designed a novel architecture using the attention mechanism. This architecture, which is called as Transformer, achieves parallelization by […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #AlwaysUpskilling Last Saturday 2 May 2020, our AI Lab Researcher Indrajit Singh presented a fabulous session on “Sequence to Sequence Learning and Attention in Neural Networks“. Sequence to Sequence Model :- Sequence-to-sequence learning (Seq2Seq) is about training models to convert sequences from one domain (e.g. sentences in English) to sequences in another […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars Last Saturday, AI Researcher Indrajit Singh presented a superb workshop on Dependency Parsing used in NLP. The topics covered in this workshop included :- Understand Dependency Parsing Syntactic Structure: Consistency and Dependency Dependency Grammar and Treebanks Transition-based dependency parsing Dependency Parsing involves detecting which words depend on which other words. Dependencies are […]

A new algorithm can predict fairly accurately how critics and audiences will react to movies using only plot summaries. Researchers gathered the plot summaries of 42,306 movies, many from Wikipedia, and used models to break up the summaries by sentence. A system called sentiment analysis analyzed each sentence and rated them based on whether they […]

#CellStratAILab #disrupt4.0 #WeCreateAISuperstars #AlwaysUpskilling #CellStratPrime Minutes from Saturday 22nd Feb 2020 AI Lab meetup at BLR :- Last Saturday our AI Researchers presented some amazing algorithms in the AI Lab. Graph Neural Networks :- First Pushparaj M. presented an excellent seminar on Graph Neural Networks (GNN). A Graph is a set of nodes (vertices) connected […]

Amazon Alexa’s AI team created a new machine learning-based method for training speech recognition devices that could help future models better understand regional language differences. In a paper presented to the North American Chapter of the Association for Computational Linguistics, Amazon Alexa AI senior applied science manager Young-Bum Kim and his colleagues laid out how […]