Learning to rank

• Pointwise
• Pairwise
• Batchwise
• Distillation
• Generative
• Masked Language Model
• Data Generation
• Alignment

Learning to rank is handled by various classes. Some are located in the learning module.

Listeners

Scorers

Scorers are able to give a score to a (query, document) pair. Among the scorers, some are have learnable parameters.

XPM Configxpmir.rankers.Scorer

Bases: Config, Initializable, EasyLogger, ABC

Submit type: xpmir.rankers.Scorer

Query-document scorer

A model able to give a score to a list of documents given a query

eval()

Put the model in inference/evaluation mode

getRetriever(retriever: Retriever, batch_size: int, batcher: Batcher = Config[xpmir.learning.batchers.batcher], top_k=None, device=None)

Returns a two stage re-ranker from this retriever and a scorer

Parameters:

• device – Device for the ranker or None if no change should be made

• batch_size – The number of documents in each batch

• top_k – Number of documents to re-rank (or None for all)

initialize(*args, **kwargs)

Main initialization

Calls __initialize__() once (using __initialize__())

to(device)

Move the scorer to another device

XPM Configxpmir.rankers.RandomScorer(*, random)

Bases: Scorer

Submit type: xpmir.rankers.RandomScorer

A random scorer

random: xpmir.learning.base.Random

The random number generator

XPM Configxpmir.rankers.AbstractModuleScorer

Bases: Scorer, Module

Submit type: xpmir.rankers.AbstractModuleScorer

Base class for all learnable scorer

This class provides a compute method that calls the forward method,

XPM Configxpmir.rankers.LearnableScorer

Bases: AbstractModuleScorer

Submit type: xpmir.rankers.LearnableScorer

Learnable scorer

A scorer with parameters that can be learnt

Adapters

XPM Configxpmir.rankers.adapters.ScorerTransformAdapter(*, scorer, adapter)

Bases: Scorer

Submit type: xpmir.rankers.adapters.ScorerTransformAdapter

Transforms topic and/or documents output by a scorer when rescoring documents

scorer: xpmir.rankers.Scorer

The original scorer to be transform

adapter: xpmir.letor.samplers.hydrators.SampleTransform

The list of sample transforms to apply

Utility functions

xpmir.rankers.scorer_retriever(documents: Documents, *, retrievers: RetrieverFactory, scorer: Scorer, **kwargs)

Helper function that returns a two stage retriever. This is useful when used with partial (when the scorer is not known).

Parameters:

• documents – The document collection

• retrievers – A retriever factory

• scorer – The scorer

Returns:

A retriever, calling the :meth:scorer.getRetriever

Retrievers

Scores can be used as retrievers through a xpmir.rankers.TwoStageRetriever

Samplers

Samplers provide samples in the form of records. They all inherit from:

class xpmir.letor.samplers.SerializableIterator

Bases: Iterator[T], Generic[T, State]

An iterator that can be serialized through state dictionaries.

This is used when saving the sampler state

XPM Configxpmir.letor.samplers.ModelBasedSampler(*, dataset, retriever)

Bases: Sampler

Submit type: xpmir.letor.samplers.ModelBasedSampler

Base class for retriever-based sampler

dataset: datamaestro_text.data.ir.Adhoc

The IR adhoc dataset

retriever: xpmir.rankers.Retriever

A retriever to sample negative documents

Records for training

class xpmir.letor.records.PairwiseRecord(query: Record, positive: Record, negative: Record)

Bases: object

A pairwise record is composed of a query, a positive and a negative document

class xpmir.letor.records.PointwiseRecord(topic: Record, document: Record, relevance: float | None = None)

Bases: object

A record from a pointwise sampler

Document samplers

Useful for pre-training or when learning index parameters (e.g. for FAISS).

XPM Configxpmir.documents.samplers.DocumentSampler(*, documents)

Bases: Config, ABC

Submit type: xpmir.documents.samplers.DocumentSampler

How to sample from a document store

documents: datamaestro_text.data.ir.DocumentStore

XPM Configxpmir.documents.samplers.HeadDocumentSampler(*, documents, max_count, max_ratio)

Bases: DocumentSampler

Submit type: xpmir.documents.samplers.HeadDocumentSampler

A basic sampler that iterates over the first documents

if max_count is 0, it iterates over all documents

documents: datamaestro_text.data.ir.DocumentStore

max_count: int = 0

Maximum number of documents (if 0, no limit)

max_ratio: float = 0

Maximum ratio of documents (if 0, no limit)

XPM Configxpmir.documents.samplers.RandomDocumentSampler(*, documents, max_count, max_ratio, random)

Bases: DocumentSampler

Submit type: xpmir.documents.samplers.RandomDocumentSampler

A basic sampler that iterates over the first documents

Either max_count or max_ratio should be non null

documents: datamaestro_text.data.ir.DocumentStore

max_count: int = 0

Maximum number of documents (if 0, no limit)

max_ratio: float = 0

Maximum ratio of documents (if 0, no limit)

random: xpmir.learning.base.Random

Random sampler

Adapters

XPM Configxpmir.letor.samplers.hydrators.SampleTransform

Bases: Config, ABC

Submit type: xpmir.letor.samplers.hydrators.SampleTransform

XPM Configxpmir.letor.samplers.hydrators.SampleHydrator(*, documentstore, querystore)

Bases: SampleTransform

Submit type: xpmir.letor.samplers.hydrators.SampleHydrator

Base class for document/topic hydrators

documentstore: datamaestro_text.data.ir.DocumentStore

The store for document texts if needed

querystore: xpmir.datasets.adapters.TextStore

The store for query texts if needed

XPM Configxpmir.letor.samplers.hydrators.SamplePrefixAdding(*, query_prefix, document_prefix)

Bases: SampleTransform

Submit type: xpmir.letor.samplers.hydrators.SamplePrefixAdding

Transform the query and documents by adding the prefix

query_prefix: str

The prefix for the query

document_prefix: str

The prefix for the document

XPM Configxpmir.letor.samplers.hydrators.SampleTransformList(*, adapters)

Bases: SampleTransform

Submit type: xpmir.letor.samplers.hydrators.SampleTransformList

A class which group a list of sample transforms

adapters: List[xpmir.letor.samplers.hydrators.SampleTransform]

The list of sample transform to be applied