Nitesh Pandey

At Fraunhofer Fokus with Technische Universität Berlin, I am working as a machine learning researcher. My responsibilities are here to handle the research project in the field of Natural Language Processing and develop the prototype of the research project and integrate it with the main system. Task includes: - Web scraping - Apply NLP with deep learning approaches - Semantic - Information Retrieval - Build the Unstructured intelligent matchmaking system API and deploy it in the production area.

The challenge of the thesis is to uncover coherence structures in texts, which aims to identify discourse relations that hold between textual units in the text. - Prepare Gold standard open-IE corpus by using Rhetorical structure theory and state of art open-IE. - building a recurrent neural network and convolution neural network based open-IE model to identify rhetorical relation for Open information extraction. Technology used: Python3, Deep learning(LSTM, CNN), NLTK, CoreNLP, Spacy, Google Cloud.

As an intern, I was supporting Alyne’s Development Team as ​Application Natural Language Processing (NLP) Intern for governance and risk management of large enterprises. I was developing an NLP model which maps different government regulation and enterprise policies. My role in this project as an intern had been to clean and preprocess data, implement model (using Gensim, Doc2vec, Word2Vec etc) and setting up infrastructure on Amazon Sagemaker(AWS) using Docker.

Text​ mining,​​ Intelligent Audio Analysis, Intelligent Systems, Methodological Foundation in Distributed system, Soziale und benutzerzentrierte Aspekte web-basierter Informationssysteme, Visual analytics, Context Recognition Architectures.

Internet​ Programming,​ Software​ Engineering,​ Information​ Technology​ for​ Management Of​ Enterprise,​ Software​ Testing​ and​ Quality Assurance,​ Information​ Management​ and Disaster​ Recovery,​ Mobile​ and​ E-commerce.