Print this page

VineSum: A software component for named entity extraction and clustering by SciFY

Thursday, 12 April 2018
VineSum: A software component for named entity extraction and clustering by SciFY

SciFY created a new software component for text and data mining, VineSum, addressed to developers who want to build applications in the area of agriculture & biodiversity. This innovative tool is part of the OpenMinTed infrastructure and it is ideal for researchers, consumer behaviour analysts, wine distributors, etc.

What is OpenMinTed?

OpenMinTed is an Open Mining Infrastructure for Text & Data that in the beginning of 2018 was searching for innovative applications and systems such as: new text mining, text analytics, or information extraction components and ready-to-use applications.

In this context SciFY joined the call and created VineSum. But what is VineSum?

What is VineSum?

VineSum is an open source executable software component that, given a collection of documents, it:

  1. Recognizes named entities (Named Entity Recognition), identifying four entity types:
    1. Vine varieties
    2. Persons
    3. Locations
    4. Dates
  2. Clusters documents into events, related to wine varieties but also to events.
  3. Exploits named entity recognition components, especially evolved to facilitate the use case.

VineSum’s main objective is to serve as a software component that is being offered to end-users in order to build applications in the area of agriculture & biodiversity. But how VineSum can be used?

How you can use VineSum?

Via the OpenMinTed platform, a user that doesn’t have programming experience or  specialized knowledge on natural language processing and data mining algorithms, can:

  1. Select a set of documents (corpus)
  2. Select the VineSum component
  3. Select any other components from the platform that may be needed
  4. Run an analysis pipeline via the OpenMinTed platform and use the output in order to categorize/summarize the information and/or discover any hidden or new knowledge.

So there you are: a free and innovative software tool for analyzing texts and data on your fingertips.

In the next few weeks we will share a tutorial for using VineSum. In the meantime check the VineSum’s source code here and stay tuned for more.

 

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we'll assume that you are happy to receive all cookies from this website.