A start-to-finish information-retrieval system designed to aid in policy analysis but applicable to any set of documents. Automatically chunks texts by paragraph, fixes spelling errors, cleans text, and projects paragraphs in space with neural word embeddings. Allows users to query the corpus for any topic or question, and generates a report analyzing and summarizing the relevant paragraphs.
|Package repository||View on GitHub|
Install the latest version of this package by entering the following in R:
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.