Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
41 changes: 41 additions & 0 deletions examples/run_lexical_baselines.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,41 @@
"""
Reproduce benchmark results.
"""

import workrb

if __name__ == "__main__":
# 1. Setup model and tasks
models = [
workrb.models.RandomRankingModel(),
workrb.models.TfIdfModel(tokenization="word"),
workrb.models.TfIdfModel(lowercase=False, tokenization="word"),
workrb.models.TfIdfModel(tokenization="char"),
workrb.models.TfIdfModel(lowercase=False, tokenization="char"),
workrb.models.BM25Model(),
workrb.models.BM25Model(lowercase=False),
workrb.models.EditDistanceModel(),
workrb.models.EditDistanceModel(lowercase=False),
]

# Config
langs = [
"en",
"fr",
"de",
"es",
"nl",
]
split = "test"

tasks = [
workrb.tasks.JobTitleSimilarityRanking(split=split, languages=langs),
]

results = workrb.evaluate_multiple_models(
models=models,
tasks=tasks,
output_folder_template="../results/lexical_baselines/{model_name}",
description="WorkRB demo with lexical baselines",
force_restart=True,
)
2 changes: 2 additions & 0 deletions pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,8 @@ dependencies = [
"PyYAML>=6.0",
"sentence-transformers>=5.1.0",
"pydantic>=2.11.9",
"rank-bm25>=0.2.2",
"rapidfuzz>=3.9.4",
]

[dependency-groups] # https://docs.astral.sh/uv/concepts/projects/dependencies/#development-dependencies
Expand Down
10 changes: 10 additions & 0 deletions src/workrb/models/__init__.py
Original file line number Diff line number Diff line change
Expand Up @@ -6,12 +6,22 @@
from workrb.models.bi_encoder import BiEncoderModel, ConTeXTMatchModel, JobBERTModel
from workrb.models.classification_model import RndESCOClassificationModel
from workrb.models.curriculum_encoder import CurriculumMatchModel
from workrb.models.lexical_baselines import (
BM25Model,
EditDistanceModel,
RandomRankingModel,
TfIdfModel,
)

__all__ = [
"BM25Model",
"BiEncoderModel",
"ConTeXTMatchModel",
"CurriculumMatchModel",
"EditDistanceModel",
"JobBERTModel",
"ModelInterface",
"RandomRankingModel",
"RndESCOClassificationModel",
"TfIdfModel",
]
Loading