AI Assistant at your service
Imagine an AI that truly understands the content of images, videos, written and spoken texts as you do.
We are always in a quest of Information. However there is difference in information and knowledge. Information Retrieval or web search is mature and we can get relevant information at our finger tips. Sifting through lots of documents (including handwritten ones) can be difficult and time consuming. Without an abstract or summary, it can take some time just to figure out what the heck someone is talking about in a paper or report. And, if you need to get through hundreds of documents – good luck at that.
This is where text summarisation comes into play. Text summarisation is part of the field of natural language processing, which is how computers can analyse, understand, and derive meaning from human language.
Hope that’s getting your thoughts flowing…..
Now, top that with the ability of querying those documents. Yes, you read that right. Be able to ask a question related to the documents and be provided with a relevant answer.
Summarisation and Question Answering is a specialized form of Information Retrieval which seeks knowledge. We are not only interested in getting the relevant pages but we are interested in getting specific answer to queries.
Recently, Summarisation and Question Answering have gathered a powerful momentum with advances in Deep Learning, which has become an essential tool for NLP (Natural Language Processing) and NLU (Natural Language Understanding).
Having an intelligent assistant will be an indispensable part of the user experience, enabling users to quickly get answers to their questions and delegate various tasks to AI-powered software. This is where Planet AI come in.
PLANETBRAIN Summariser module
Business heads, analysts, paralegals, health professionals and academic researchers need to comb through huge numbers of documents every day to keep ahead, and a large portion of their time is spent just figuring out what document is relevant and what isn’t. By extracting important sentences and creating comprehensive summaries, it’s possible to quickly assess whether or not a document is worth reading.
PlanetBrain Summariser module scans through large documents including handwritten notes/documents and returns the sentences that are most likely useful for generating a summary.
PLANETBRAIN Question Answering module
Question Answering is a specialized form of Information Retrieval which seeks knowledge. We are not only interested in getting the relevant pages but we are interested in getting specific answer to queries.
PlanetBrain QA module predicts the best answer for a query, given a passage or a set of passages that contain the answer to that query. It then predicts the best candidate answers by studying the passage and queries interactively and evaluates various contextual relationships between them. Word sequences of both query (question) and context (passage) are projected into distributed representations and encoded by recurrent neural mechanisms. The attention mechanism is then used to model the complex interaction between the query and the context. A pointer network is then employed to predict the boundary of the answer.