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

Tutorial 12: add introduction #2798

Merged
merged 3 commits into from
Jul 13, 2022
Merged

Tutorial 12: add introduction #2798

merged 3 commits into from
Jul 13, 2022

Conversation

vblagoje
Copy link
Member

Related Issue(s): ...
This PR resolves the documentation issue with the LFQA tutorial. For more details see #2623

@review-notebook-app
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/deepset-ai/haystack/blob/master/tutorials/Tutorial12_LFQA.ipynb)"
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/deepset-ai/haystack/blob/master/tutorials/Tutorial12_LFQA.ipynb)\n",
"\n",
"This tutorial shows how to build and use a pipeline for generative question answering, in particular, a task usually referred to as Long-Form Question Answering (LFQA). These systems function by querying large document stores for relevant information and subsequently using the retrieved documents to generate accurate, multi-sentence answers. The retrieved documents related to a given query, colloquially called context passages, are not used merely as source tokens for extracted answers, but instead provide a larger context for the synthesis of original, abstractive long-form answers."
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How about changing it a bit to make the sentences simpler:
Follow this tutorial to learn how to build and use a pipeline for Long-Form Question Answering (LFQA). LFQA is a variety of the generative question answering task. LFQA systems query large document stores for relevant information and then use this information to generate accurate, multi-sentence answers. In a regular question answering system, the retrieved documents related to the query (context passages) act as source tokens for extracted answers. In an LFQS system, context passages provide the context the system uses to generate original, abstractive, long-form answers.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@vblagoje
Copy link
Member Author

Should be gtg now @agnieszka-m

@vblagoje vblagoje marked this pull request as draft July 13, 2022 12:59
@vblagoje vblagoje self-assigned this Jul 13, 2022
@vblagoje vblagoje marked this pull request as ready for review July 13, 2022 13:00
@ZanSara ZanSara mentioned this pull request Jul 13, 2022
2 tasks
@masci masci merged commit 2a7e333 into deepset-ai:master Jul 13, 2022
@vblagoje
Copy link
Member Author

Thanks @masci

Krak91 pushed a commit to Krak91/haystack that referenced this pull request Jul 26, 2022
* Tutorial 12: add introduction

* PR review for Tutorial 12: add introduction

* Update Documentation & Code Style

Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
@vblagoje vblagoje deleted the tutorial_lfqa_intro branch February 28, 2023 12:08
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

Successfully merging this pull request may close these issues.

None yet

4 participants