Merge and sequence different sections from input package consisting of text, figures, tables etc.
₹1250-2500 INR / hour
Κλειστή
Αναρτήθηκε πάνω από 6 χρόνια πριν
₹1250-2500 INR / hour
Task
• Classify different sections of a document and output the sequenced sections as per input specifications
Required Skill set
1. Word Document (.docx) Understanding
• Understanding of the internal storage of word documents i.e. xml for text part and objects (figures, tables, equations (Word equations and Mathtype))
2. NLP Experience
• Extracting features from text provided
• Libraries like Python-NLTK/Stanford NER etc. or other libraries can be used to accomplish this
3. Machine Learning Experience
• Familiar with building classification models like SVMs, Random Forest, Neural Networks etc.
• ML Libraries like scikit-learn, statsmodels etc. or WEKA etc. can be used to build the classification models
Detailed requirements will be shared with selected vendors.
i am a python developer and i did develop many project in python and i use machine learning libraries to build intelligent applications like keras, TensorFlow and Scikit learn and graph lab in python, i have vast experience in python, i am already working on word parser and pdf-parser for parsing document and i can share detail let me know when you are ready, i have 2+ years of experience in NLP/NLU/ML