LAION-AI / LAION-AI/Open-Assistant

Proposal: Use scientific papers for data.

Open
#1,927 1 comment 2 reactions 1 assignee View on GitHub

@juanjfndz is already working on this.

Since Mar 2, 2023.

data
Dominant language
Python
Stars
37.4k
Forks
3.3k
PR merge metrics
No merged PRs in 30d

Description

Proposal:
What about using open access publications from arXiv to generate a conversational AI system that can provide answers to questions related to scientific papers. As arXiv encourages choosing a liberal license for re-use of the papers (https://info.arxiv.org/help/license/index.html), I think it would be a valuable resource.

Implementation:
We can use a question-and-answer format that can extract information from the scientific papers. We could think like a scientific person who needs to write a paper (this is also value for essay data). Here is an example of how the conversational AI system can be used:

Abstract generation:
Question: Could you write an abstract for this title <title>?
Answer: Certainly! Here's an example of a possible abstract:

Title suggestion:
Question: What could be a great title for this abstract: ?
Answer: Here's a possible title for your abstract: <title>

Section content suggestion:
Question: I am writing a paper about this <title>. I have talked about these previous sections and now I have to write about this

. Could you give me an example?
Answer: Certainly! Here's an example of what you can write for your section:

And more: Summary generation, Orthography correction (with a manipulation of the text), Citation recommendation...

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.