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

Add trec covid baseline queries #1142

Merged
merged 6 commits into from May 5, 2020

Conversation

lukuang
Copy link
Collaborator

@lukuang lukuang commented May 4, 2020

In this PR I:

  • add the query file for round1 of udel_fang_run3.
  • add the query file for round2 generated the same way above
  • add the python script to generate these files

@codecov
Copy link

codecov bot commented May 4, 2020

Codecov Report

Merging #1142 into master will decrease coverage by 0.22%.
The diff coverage is n/a.

Impacted file tree graph

@@             Coverage Diff              @@
##             master    #1142      +/-   ##
============================================
- Coverage     47.91%   47.68%   -0.23%     
+ Complexity      715      705      -10     
============================================
  Files           144      144              
  Lines          8303     8303              
  Branches       1184     1184              
============================================
- Hits           3978     3959      -19     
- Misses         3988     4007      +19     
  Partials        337      337              
Impacted Files Coverage Δ Complexity Δ
...java/io/anserini/ltr/feature/CountBigramPairs.java 64.93% <0.00%> (-24.68%) 23.00% <0.00%> (-10.00%)

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update d9e863e...d474267. Read the comment docs.

<topics batch="1" task="COVIDSearch 2020">
<topic number="1">
<query>coronavirus origin origin COVID-19</query>
<question>what is the origin of COVID-19</question>
Copy link
Member

Choose a reason for hiding this comment

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

What if we just kept query and removed question and narrative - just to reduce confusion?

@lukuang
Copy link
Collaborator Author

lukuang commented May 5, 2020

Effectiveness using the round 1 query in this PR:

  • bm25: 0.5826

Effectiveness using different fields:

  • query+bm25: 0.4099
  • question+bm25: 0.5179

Experiments were done using Cord19AbstractCollection

@lintool lintool self-requested a review May 5, 2020 02:22
@lintool lintool merged commit 0d4bcd5 into castorini:master May 5, 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

Successfully merging this pull request may close these issues.

None yet

2 participants