Skip to content

Updated regressions to new Persian analyzer #3100

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.

Sign up for GitHub

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

Merged
lintool merged 1 commit into from
Jan 25, 2026
Merged

Updated regressions to new Persian analyzer #3100

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion bin/run.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,8 @@
#!/bin/sh

java -cp `ls target/*-fatjar.jar` -Xms512M -Xmx192G -Dslf4j.internal.verbosity=WARN --add-modules jdk.incubator.vector $@ 2>&1 | grep -v "WARNING: Using incubator modules"
java -cp `ls target/*-fatjar.jar` -Xms512M -Xmx192G -Dslf4j.internal.verbosity=WARN --add-modules jdk.incubator.vector --enable-native-access=ALL-UNNAMED $@ 2>&1 | grep -v "WARNING: Using incubator modules"

# Notes:
# - "WARNING: Using incubator modules: jdk.incubator.vector" cannot be suppressed, so just grep -v it.
# - "SLF4J(I): Connected with provider of type [org.apache.logging.slf4j.SLF4JServiceProvider]": suppress using -Dslf4j
# - "WARNING: A restricted method in java.lang.foreign.Linker has been called" fixed by --enable-native-access=ALL-UNNAMED
24 changes: 12 additions & 12 deletions docs/regressions/regressions-hc4-neuclir22-fa.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,21 +156,21 @@ With the above commands, you should be able to reproduce the following results:

| **MAP** | **BM25 (default)**| **+RM3** | **+Rocchio**|
|:-------------------------------------------------------------------------------------------------------------|-------------------|-----------|-------------|
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.1198 | 0.1064 | 0.1221 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.1435 | 0.0833 | 0.1254 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.1438 | 0.1075 | 0.1351 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.1331 | 0.1045 | 0.1318 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.1420 | 0.0998 | 0.1250 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.1536 | 0.1255 | 0.1382 |
| **nDCG@20** | **BM25 (default)**| **+RM3** | **+Rocchio**|
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.1806 | 0.1564 | 0.1794 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.2288 | 0.1285 | 0.1968 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.2233 | 0.1706 | 0.2001 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.1999 | 0.1532 | 0.1847 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.2197 | 0.1526 | 0.1926 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.2371 | 0.1925 | 0.2057 |
| **J@20** | **BM25 (default)**| **+RM3** | **+Rocchio**|
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.1430 | 0.1220 | 0.1520 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.1480 | 0.1110 | 0.1480 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.1570 | 0.1210 | 0.1530 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.1510 | 0.1270 | 0.1650 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.1490 | 0.1120 | 0.1580 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.1670 | 0.1270 | 0.1690 |
| **Recall@1000** | **BM25 (default)**| **+RM3** | **+Rocchio**|
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.7234 | 0.6742 | 0.7929 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.7431 | 0.6132 | 0.7768 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.7652 | 0.6436 | 0.8058 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.7483 | 0.6933 | 0.7991 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.7475 | 0.6365 | 0.8233 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.7964 | 0.6835 | 0.8532 |

The above results reproduce the BM25 title queries run in Table 2 of [this paper](https://arxiv.org/pdf/2201.08471.pdf).

Expand Down
48 changes: 24 additions & 24 deletions docs/regressions/regressions-hc4-v1.0-fa.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -245,33 +245,33 @@ With the above commands, you should be able to reproduce the following results:

| **MAP** | **BM25 (default)**| **+RM3** | **+Rocchio**|
|:-------------------------------------------------------------------------------------------------------------|-------------------|-----------|-------------|
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.2971 | 0.2865 | 0.3030 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.3243 | 0.3402 | 0.3721 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.3366 | 0.2919 | 0.3881 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.2877 | 0.2954 | 0.2954 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.2928 | 0.2807 | 0.2928 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.3285 | 0.3042 | 0.3274 |
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.2818 | 0.2583 | 0.2761 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.3128 | 0.2984 | 0.3442 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.3343 | 0.2680 | 0.3510 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.3059 | 0.3080 | 0.3182 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.3108 | 0.2714 | 0.3170 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.3437 | 0.3058 | 0.3507 |
| **nDCG@20** | **BM25 (default)**| **+RM3** | **+Rocchio**|
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.3445 | 0.3446 | 0.3161 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.3475 | 0.3862 | 0.3895 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.3665 | 0.3454 | 0.3962 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.3846 | 0.3812 | 0.3861 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.4039 | 0.3755 | 0.3811 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.4489 | 0.4049 | 0.4256 |
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.3315 | 0.3186 | 0.2806 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.3394 | 0.3508 | 0.3599 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.3664 | 0.3132 | 0.3490 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.4114 | 0.3982 | 0.3958 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.4077 | 0.3513 | 0.3942 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.4606 | 0.4006 | 0.4341 |
| **J@20** | **BM25 (default)**| **+RM3** | **+Rocchio**|
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.4100 | 0.3300 | 0.3950 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.4750 | 0.3500 | 0.5100 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.4700 | 0.3450 | 0.5250 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.4010 | 0.3800 | 0.4350 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.3890 | 0.3590 | 0.4300 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.4420 | 0.3800 | 0.4580 |
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.3900 | 0.3500 | 0.3650 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.4600 | 0.3300 | 0.4650 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.4600 | 0.2900 | 0.4800 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.4220 | 0.4030 | 0.4600 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.3950 | 0.3410 | 0.4570 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.4460 | 0.3980 | 0.4840 |
| **Recall@1000** | **BM25 (default)**| **+RM3** | **+Rocchio**|
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.7794 | 0.7683 | 0.8039 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.8491 | 0.7737 | 0.8838 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.9129 | 0.8102 | 0.9154 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.8223 | 0.7755 | 0.8560 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.8402 | 0.7487 | 0.8738 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.8651 | 0.8055 | 0.8883 |
| [HC4 (Persian): dev-topic title](https://github.com/hltcoe/HC4) | 0.7745 | 0.7835 | 0.8039 |
| [HC4 (Persian): dev-topic description](https://github.com/hltcoe/HC4) | 0.8433 | 0.7685 | 0.8727 |
| [HC4 (Persian): dev-topic description+title](https://github.com/hltcoe/HC4) | 0.9128 | 0.8077 | 0.9323 |
| [HC4 (Persian): test-topic title](https://github.com/hltcoe/HC4) | 0.8405 | 0.7957 | 0.8721 |
| [HC4 (Persian): test-topic description](https://github.com/hltcoe/HC4) | 0.8581 | 0.7488 | 0.8853 |
| [HC4 (Persian): test-topic description+title](https://github.com/hltcoe/HC4) | 0.8799 | 0.8051 | 0.9035 |

The above results reproduce the BM25 title queries run in Table 2 of [this paper](https://arxiv.org/pdf/2201.08471.pdf).

Expand Down
4 changes: 2 additions & 2 deletions docs/regressions/regressions-miracl-v1.0-fa-aca.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -57,6 +57,6 @@ With the above commands, you should be able to reproduce the following results:

| **nDCG@10** | **BM25** |
|:-------------------------------------------------------------------------------------------------------------|-----------|
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.3427 |
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.3576 |
| **R@100** | **BM25** |
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.7600 |
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.7806 |
4 changes: 2 additions & 2 deletions docs/regressions/regressions-miracl-v1.0-fa.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -55,6 +55,6 @@ With the above commands, you should be able to reproduce the following results:

| **nDCG@10** | **BM25** |
|:-------------------------------------------------------------------------------------------------------------|-----------|
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.3334 |
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.3568 |
| **R@100** | **BM25** |
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.7306 |
| [MIRACL (Persian): dev](https://github.com/project-miracl/miracl) | 0.7413 |
Loading