Build legal domain product from scratch with bellow features.
Document Classification, Text Summarization, Custom Entity Extraction, Clause extraction and Classification, File
Deduplication using Document Similarity, OCR, Attribute(Language,Currency, Type, Title, Date etc.) Detection,
Feedback Loop with Auto Training, File Deduplication
Technology used : Java, Python, Mallet, CNN, RNN, LSTM, CRF Suite, Stanford NER, OpenNLP, Apache Tika

BibAnalyser use to categorize content of the reference which is published in research paper. It use to organize content
of the reference like author name, paper title, journal title, publication year etc. Machine Learning and Natural
Language Processing is used to find the semantic of each word and categorize it.
Technology used : Java, CRF++ API, CRF Suite, Stanford NLP, Restlet

Smart Street is low-cost intelligent transportation systems (ITS) solutions that analyze current traffic using IoT and
Machine Learning. Responsible for developing the whole machine cycle that contains data pre-procession, Attribute
selection, Classification, and Validation.
Technology used : Java, Weka, R Programming