Skip to content

Docs: Performance Comparison of Python versus Java RM3 and Rocchio Implementations#2420

Open
nourj98 wants to merge 3 commits intocastorini:masterfrom
nourj98:master
Open

Docs: Performance Comparison of Python versus Java RM3 and Rocchio Implementations#2420
nourj98 wants to merge 3 commits intocastorini:masterfrom
nourj98:master

Conversation

@nourj98
Copy link
Copy Markdown
Member

@nourj98 nourj98 commented Feb 18, 2026

Adding experimental documentation of RM3 and Rocchio Python implementations

This document compares the performance of RM3 and Rocchio implementations in Python versus Java, including effectiveness and latency metrics across multiple datasets.

### Effectiveness Comparison

<table align="center" style="border-collapse: collapse;">
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Ask an LLM to change this into markdown? No need for HTML and formatting here...

Copy link
Copy Markdown
Member Author

Choose a reason for hiding this comment

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

Should be fixed now!

Switched from html to markdown
@@ -0,0 +1,83 @@
# Pyserini: Performance Comparison of Python versus Java RM3 and Rocchio Implementations
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

extra space before RM3

@@ -0,0 +1,83 @@
# Pyserini: Performance Comparison of Python versus Java RM3 and Rocchio Implementations

We fully re-implmented the RM3 and Rocchio implementations from Anserini in Python. Below is a comparison of the performance of RM3 and Rocchio in Python versus in Java.
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Add a date somewhere, these experiments were from...

### Effectiveness Comparison: Python versus Java

| Implementation | RM3 MAP | RM3 nDCG@10 | RM3 Recall@1000 | Rocchio MAP | Rocchio nDCG@10 | Rocchio Recall@1000 |
|---------------|---------|-------------|-----------------|-------------|------------------|----------------------|
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Better MD table alignment? e.g., header row doesn't line up.

Also add : to better control alignment?

Below also...

| Implementation | RM3 | Rocchio |
|---------------|---------|----------|
| **TREC DL19** | | |
| Python | 3.67 | 4.14 |
Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

maybe right align numbers?

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.

2 participants