This is a demo of an intelligence resume search we built using Latent Semantic Indexing (LSI) to build semantically ordered indexes of 100 resumes. From this index, we can query resumes by keyword search or by giving a reference resume to match. The top 5 resumes that has the highest similarity scores based will be returned.
We trained a NLP model to automatically extract intents from FAQs in our website. We then proceeded to train a chat bot with these intents.
We trained a Multinomial Naive Bayes algorithm to classify any text into one of 20 categories. This algorithm is trained on a dataset of 8000 emails and can classify the emails into these 20 categories based on their subject and body text. This algorithm is hosted in a web portal and hosted at this url http://18.104.22.168:3500 for those who are interested in trying it out
We built lexical rules that can generate questions from a body of text. Then we used those questions as intents and trained a chat bot using IBM watson. This automatic intent generation is an important area for building novel NLP models. This enables us to build chat bots that can learn automatically from a body of text like archived client convesations, HR policy manuals etc.,