Proposed Session

NLP and Drupal 8

Speaker(s)
Gaurav Kapoor, Pritish Kumar
Proposed Track(s)
Beyond Drupal
Level of expertise
Intermediate
Session Type
Regular (45 min)

NLP can be leveraged to solve various problems related to content tagging, related content and content summary. These are some of the most common requirements in modern CMS and media/publishing websites. 

Most of the time we show related content using Tags. In that case, we have to make sure that the editor/content writer are populating accurate tags in each and every content they add. This approach has various shortcomings. In the case of a large content base, we will have a lot of tags and it becomes difficult to select the right tag for each and every content. In the case when no tags are provided we either see default articles in Related sections or we don't see any. We need something which automatically fills tags and we don't see any break in logic which is based on them.

 In this session, we are going to explore

1. Usage of NLP techniques to auto-tag content.

2. Automatically generate the summary for the content.

3. Reduce duplicate content.