Papers
To ease the reproduction of papers, and the upload of full models on HuggingFace, the xpmir.papers package can be used.
Configuration
Papers experimental parameters are defined by data classes. The main
one is xpmir.papers.helpers.PaperExperiment that
defines an id (for experimaestro), a title and a description.
These informations can be used e.g. when uploading the trained
models on HuggingFace.
- xpmir.papers.helpers.PaperExperiment
alias of
ConfigurationBase
- class xpmir.papers.helpers.NeuralIRExperiment(*, id: str = '???', file: str = 'experiment', module: str | None = None, pythonpath: List[str] | None = None, parent: str | None = None, title: str = '', subtitle: str = '', paper: str = '', description: str = '', add_timestamp: bool = False, gpu: bool = True, use_best_device: bool = False, seed: int = 0)[source]
Bases:
ConfigurationBaseSettings most neural IR experiments
- add_timestamp: bool
Adds a timestamp YYYY_MM_DD-HH_MM to the experiment ID
- description: str
Description of the experiment
- file: str
Relative path of the file containing a run function
- gpu: bool
Use GPU for computation
- id: str
ID of the experiment
This ID is used by experimaestro when running as the experiment.
- module: str | None
Relative path of the file containing a run function
- paper: str
Source paper for this experiment
- parent: str | None
Relative path of a YAML file that should be merged
- pythonpath: List[str] | None
Python path relative to the parent directory of the YAML file
- seed: int
The seed used for experiments
- subtitle: str
Allows to give some more details about the experiment
- title: str
Short description of the experiment
- use_best_device: bool
Use best GPU device
Helpers
Pipelines factorize the code necessary to run some experiments: for instance, training re-rankers on MS-Marco is usually performed with similar training data, evaluation datasets.
Implemented papers
This page give some information about reproduction of papers based on XPMIR.
-
monoBERT