Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Improving schema.org:description for websites using BERT extractive summarization #980

Closed
cyberandy opened this issue Nov 27, 2019 · 0 comments
Assignees
Milestone

Comments

@cyberandy
Copy link
Member

cyberandy commented Nov 27, 2019

The goal here is to let WordLift summarize the content of an article or the description of an entity using BERT. The resulting summary shall be stored as schema.org:description.

A default ratio of sentences would work for the expected summary. We can further revise these parameters but currently to obtain a good summary with a limited number of words we can use min_length=60 and ratio=0.005. To support the languages we already deal with we shall use bert-base-multilingual-cased

@cyberandy cyberandy changed the title Improving schema.org:description for English websites using BERT extractive summarization Improving schema.org:description for websites using BERT extractive summarization Dec 2, 2019
@akshayraje akshayraje modified the milestones: 3.25.0, 3.26.0 Feb 3, 2020
@ziodave ziodave assigned ziodave and naveen17797 and unassigned ziodave Feb 28, 2020
naveen17797 added a commit that referenced this issue Mar 5, 2020
naveen17797 added a commit that referenced this issue Mar 5, 2020
naveen17797 added a commit that referenced this issue Mar 5, 2020
naveen17797 added a commit that referenced this issue Mar 5, 2020
naveen17797 added a commit that referenced this issue Mar 6, 2020
naveen17797 added a commit that referenced this issue Mar 10, 2020
naveen17797 added a commit that referenced this issue Mar 10, 2020
naveen17797 added a commit that referenced this issue Mar 12, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

4 participants