After testing the discovery service, it seems useless to me at least or I might be missing something.
When I query, it matches the document and returns the whole document. If my document is huge, then for all queries it returns the whole document matching the query text, which is useless.
Now Do I have to create a separate document for every query?
If that's the case, API.AI or WIT.AI is a better option.
Please clear me on what I am missing in here!
You can upload data in the following document formats: Word, PDF, HTML, and JSON documents. Data input can also be in binary format; this makes it easier to upload PDF and Word documents containing rich media content. The data is converted and enriched to make it easier to explore and discover insights.
When dealing with an enormous amount of text documents, Watson Discovery is a valuable tool to optimize your workflow by applying the Natural Language Processing (NLP) algorithm to extract, valuable information, sentiment, concepts, semantic roles from your collection of documents.
IBM Watson Discovery empowers document search with artificial intelligence (AI) enhanced text analysis. Companies use the document search capabilities to index and search documents rapidly to enhance and power internal research, customer service, or chatbox services.
A common way to use Discovery is by accessing the Discovery APIs from your application. The Watson team releases SDKs that support many programming languages so that you can use Discovery easily in a web or mobile application. All of the data content is stored and enriched within Watson Discovery collections.
For now with Discovery, you would need to break up your documents once to put them in a collection, then any query against the collection in Discovery will return results from that set of separated docs. So if your documents don't change, this split should be a one time action.
Though the solution of automatically identifying the relevant section of a larger doc for a query is a good consideration for Discovery (note: I work for IBM Watson).
If you love us? You can donate to us via Paypal or buy me a coffee so we can maintain and grow! Thank you!
Donate Us With