Neural models

Cross-Encoder

Models that rely on a joint representation of the query and the document.

XPM Configxpmir.neural.cross.CrossScorer(*, checkpoint, encoder)[source]

Bases: xpmir.neural.TorchLearnableScorer, xpmir.distributed.DistributableModel

Query-Document Representation Classifier

Based on a query-document representation representation (e.g. BERT [CLS] token). AKA Cross-Encoder

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

encoder: xpmir.text.encoders.DualTextEncoder

an encoder for encoding the concatenated query-document tokens which doesn’t contains the final linear layer

XPM Configxpmir.neural.cross.DuoCrossScorer(*, checkpoint, encoder)[source]

Bases: xpmir.rankers.DuoLearnableScorer, xpmir.distributed.DistributableModel

Query-document-document Representation classifier based on Bert The encoder usually refer to the encoder of type DualDuoBertTransformerEncoder()

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

encoder: xpmir.text.encoders.TripletTextEncoder

The encoder to use for the Duobert model

Dual models

Dual models compute a separate representation for documents and queries, which allows some speedup when computing scores of several documents and/or queries.

XPM Configxpmir.neural.DualRepresentationScorer(*, checkpoint)[source]

Bases: xpmir.neural.TorchLearnableScorer

Neural scorer based on (at least a partially) independent representation of the document and the question.

This is the base class for all scorers that depend on a map of cosine/inner products between query and document tokens.

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

score_pairs(queries, documents, info: Optional[xpmir.learning.context.TrainerContext]) <Mock name='mock.Tensor' id='140030920749840'>[source]

Score the specified pairs of queries/documents.

There are as many queries as documents. The exact type of queries and documents depends on the specific instance of the dual representation scorer.

Parameters
  • queries (Any) – The list of encoded queries

  • documents (Any) – The matching list of encoded documents

  • info (Optional[TrainerContext]) – _description_

Returns

A tensor of dimension (N) where N is the number of documents/queries

Return type

torch.Tensor

score_product(queries, documents, info: Optional[xpmir.learning.context.TrainerContext]) <Mock name='mock.Tensor' id='140030920749840'>[source]

Computes the score of all possible pairs of query and document

Parameters
  • queries (Any) – The encoded queries

  • documents (Any) – The encoded documents

  • info (Optional[TrainerContext]) – The training context (if learning)

Returns

A tensor of dimension (N, P) where N is the number of queries and P the number of documents

Return type

torch.Tensor

XPM Configxpmir.neural.dual.DualVectorScorer(*, checkpoint)[source]

Bases: xpmir.neural.DualRepresentationScorer

A scorer based on dual vectorial representations

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

Hooks

XPM Configxpmir.neural.dual.DualVectorListener[source]

Bases: xpmir.learning.context.TrainingHook

Listener called with the (vectorial) representation of queries and documents

The hook is called just after the computation of documents and queries representations.

This can be used for logging purposes, but more importantly, to add regularization losses such as the FlopsRegularizer regularizer.

__call__(context: xpmir.learning.context.TrainerContext, queries: <Mock name='mock.Tensor' id='140030920749840'>, documents: <Mock name='mock.Tensor' id='140030920749840'>)[source]

Hook handler

Parameters
  • context (TrainerContext) – The training context

  • queries (torch.Tensor) – The query vectors

  • documents (torch.Tensor) – The document vectors

Raises

NotImplementedError – _description_

XPM Configxpmir.neural.dual.FlopsRegularizer(*, lambda_q, lambda_d)[source]

Bases: xpmir.neural.dual.DualVectorListener

The FLOPS regularizer computes

\[FLOPS(q,d) = \lambda_q FLOPS(q) + \lambda_d FLOPS(d)\]

where

\[FLOPS(x) = \left( \frac{1}{d} \sum_{i=1}^d |x_i| \right)^2\]
lambda_q: float

Lambda for queries

lambda_d: float

Lambda for documents

XPM Configxpmir.neural.dual.ScheduledFlopsRegularizer(*, lambda_q, lambda_d, min_lambda_q, min_lambda_d, lamdba_warmup_steps)[source]

Bases: xpmir.neural.dual.FlopsRegularizer

The FLOPS regularizer where the lamdba_q and lambda_d varie according to the steps. The lambda values goes quadratic before the `lamdba_warmup_steps`, and then remains constant

lambda_q: float

Lambda for queries

lambda_d: float

Lambda for documents

min_lambda_q: float = 0

Min value for the lambda_q before it increase

min_lambda_d: float = 0

Min value for the lambda_d before it increase

lamdba_warmup_steps: int = 0

The warmup steps for the lambda

Dense models

XPM Configxpmir.neural.dual.Dense(*, checkpoint, encoder, query_encoder)[source]

Bases: xpmir.neural.dual.DualVectorScorer

A scorer based on a pair of (query, document) dense vectors

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

encoder: xpmir.text.encoders.TextEncoder

The document (and potentially query) encoder

query_encoder: xpmir.text.encoders.TextEncoder

The query encoder (optional, if not defined uses the query_encoder)

classmethod from_sentence_transformers(hf_id: str, **kwargs)[source]

Creates a dense model from a Sentence transformer

The list can be found on HuggingFace https://huggingface.co/models?library=sentence-transformers

Parameters

hf_id – The HuggingFace ID

XPM Configxpmir.neural.dual.DotDense(*, checkpoint, encoder, query_encoder)[source]

Bases: xpmir.neural.dual.Dense, xpmir.distributed.DistributableModel

Dual model based on inner product.

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

encoder: xpmir.text.encoders.TextEncoder

The document (and potentially query) encoder

query_encoder: xpmir.text.encoders.TextEncoder

The query encoder (optional, if not defined uses the query_encoder)

XPM Configxpmir.neural.dual.CosineDense(*, checkpoint, encoder, query_encoder)[source]

Bases: xpmir.neural.dual.Dense

Dual model based on cosine similarity.

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

encoder: xpmir.text.encoders.TextEncoder

The document (and potentially query) encoder

query_encoder: xpmir.text.encoders.TextEncoder

The query encoder (optional, if not defined uses the query_encoder)

Interaction models

xpmir.neural.interaction.InteractionScorer

Interaction-based neural scorer

xpmir.neural.interaction.drmm.Drmm

Deep Relevance Matching Model (DRMM)

xpmir.neural.colbert.Colbert

ColBERT model

XPM Configxpmir.neural.interaction.InteractionScorer(*, checkpoint, vocab, qlen, dlen)[source]

Bases: xpmir.neural.TorchLearnableScorer

Interaction-based neural scorer

This is the base class for all scorers that depend on a map of cosine/inner products between query and document token representations.

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

vocab: xpmir.text.encoders.TokensEncoder

The embedding model – the vocab also defines how to tokenize text

qlen: int = 20

Maximum query length (this can be even shortened by the model)

dlen: int = 2000

Maximum document length (this can be even shortened by the model)

XPM Configxpmir.neural.interaction.drmm.Drmm(*, checkpoint, vocab, qlen, dlen, hist, hidden, index, combine)[source]

Bases: xpmir.neural.interaction.InteractionScorer

Deep Relevance Matching Model (DRMM)

Implementation of the DRMM model from:

Jiafeng Guo, Yixing Fan, Qingyao Ai, and William Bruce Croft. 2016. A Deep Relevance Matching Model for Ad-hoc Retrieval. In CIKM.

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

vocab: xpmir.text.encoders.TokensEncoder

The embedding model – the vocab also defines how to tokenize text

qlen: int = 20

Maximum query length (this can be even shortened by the model)

dlen: int = 2000

Maximum document length (this can be even shortened by the model)

hist: xpmir.neural.interaction.drmm.CountHistogram = xpmir.neural.interaction.drmm.LogCountHistogram(nbins=29)

The histogram type

hidden: int = 5

Hidden layer dimension for the feed forward matching network

index: datamaestro_text.data.ir.AdhocIndex

The index (only used when using IDF to combine)

combine: xpmir.neural.interaction.drmm.Combination = xpmir.neural.interaction.drmm.IdfCombination()

How to combine the query term scores

XPM Configxpmir.neural.colbert.Colbert(*, checkpoint, vocab, qlen, dlen, masktoken, querytoken, doctoken, similarity, linear_dim, compression_size)[source]

Bases: xpmir.neural.interaction.InteractionScorer

ColBERT model

Implementation of the Colbert model from:

Khattab, Omar, and Matei Zaharia. “ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT.” SIGIR 2020, Xi’An, China

For the standard Colbert model, use BERT as the vocab(ulary)

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

vocab: xpmir.text.encoders.TokensEncoder

The embedding model – the vocab also defines how to tokenize text

qlen: int = 20

Maximum query length (this can be even shortened by the model)

dlen: int = 2000

Maximum document length (this can be even shortened by the model)

version: int = 2constant

Current version of the code (changes when a bug is found)

masktoken: bool = True

Whether a [MASK] token should be used instead of padding

querytoken: bool = True

Whether a specific query token should be used as a prefix to the question

doctoken: bool = True

Whether a specific document token should be used as a prefix to the document

similarity: xpmir.neural.colbert.Similarity = xpmir.neural.colbert.CosineDistance()

Which similarity to use

linear_dim: int = 128

Size of the last linear layer (before computing inner products)

compression_size: int = 128

Projection layer for the last layer (or 0 if None)

Sparse Models

XPM Configxpmir.neural.splade.SpladeTextEncoder(*, encoder, aggregation, maxlen)[source]

Bases: xpmir.text.encoders.TextEncoder, xpmir.distributed.DistributableModel

Splade model

It is only a text encoder since the we use xpmir.neural.dual.DotDense as the scorer class

encoder: xpmir.text.huggingface.TransformerTokensEncoder

The encoder from Hugging Face

aggregation: xpmir.neural.splade.Aggregation

How to aggregate the vectors

maxlen: int

Max length for texts

XPM Configxpmir.neural.splade.Aggregation[source]

Bases: experimaestro.core.objects.Config

The aggregation function for Splade

XPM Configxpmir.neural.splade.MaxAggregation[source]

Bases: xpmir.neural.splade.Aggregation

Aggregate using a max

XPM Configxpmir.neural.splade.SumAggregation[source]

Bases: xpmir.neural.splade.Aggregation

Aggregate using a sum

From Huggingface

XPM Configxpmir.neural.huggingface.HFCrossScorer(*, checkpoint, hf_id, max_length)[source]

Bases: xpmir.neural.TorchLearnableScorer, xpmir.distributed.DistributableModel

Load a cross scorer model from the huggingface

checkpoint: Path

A checkpoint path from which the model should be loaded (or None otherwise)

hf_id: str

the id for the huggingface model

max_length: int

the max length for the transformer model