NeuML/biomedbert-small-colbert

BiomedBERT Small ColBERT

This is a PyLate model finetuned from neuml/biomedbert-small. It maps sentences & paragraphs to sequences of 128-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator.

Usage (txtai)

This model can be used to build embeddings databases with txtai for semantic search and/or as a knowledge source for retrieval augmented generation (RAG). Note that since this is a custom architecture, trust_remote_code is required to be enabled.

import txtai

embeddings = txtai.Embeddings(
  path="neuml/biomedbert-small-colbert",
  content=True
)
embeddings.index(documents())

# Run a query
embeddings.search("query to run")

Late interaction models excel as reranker pipelines.

from txtai.pipeline import Reranker, Similarity

similarity = Similarity(path="neuml/biomedbert-small-colbert", lateencode=True)
ranker = Reranker(embeddings, similarity)
ranker("query to run")

Usage (PyLate)

Alternatively, the model can be loaded with PyLate.

from pylate import rank, models

queries = [
    "query A",
    "query B",
]

documents = [
    ["document A", "document B"],
    ["document 1", "document C", "document B"],
]

documents_ids = [
    [1, 2],
    [1, 3, 2],
]

model = models.ColBERT(
    model_name_or_path="neuml/biomedbert-small-colbert", trust_remote_code=True
)

queries_embeddings = model.encode(
    queries,
    is_query=True,
)

documents_embeddings = model.encode(
    documents,
    is_query=False,
)

reranked_documents = rank.rerank(
    documents_ids=documents_ids,
    queries_embeddings=queries_embeddings,
    documents_embeddings=documents_embeddings,
)

Evaluation Results

Performance of these models are compared to previously released models trained on medical literature. The most commonly used small embeddings model is also included for comparison.

The following datasets were used to evaluate model performance.

• PubMed QA
  • Subset: pqa_labeled, Split: train, Pair: (question, long_answer)
• PubMed Subset
  • Split: test, Pair: (title, text)
• PubMed Summary
  • Subset: pubmed, Split: validation, Pair: (article, abstract)

Evaluation results are shown below. The Pearson correlation coefficient is used as the evaluation metric.

Model	PubMed QA	PubMed Subset	PubMed Summary	Average
all-MiniLM-L6-v2	90.40	95.92	94.07	93.46
biomedbert-base-colbert	94.59	97.18	96.21	95.99
biomedbert-base-embeddings	94.60	98.39	97.61	96.87
biomedbert-base-reranker	97.66	99.76	98.81	98.74
biomedbert-small-colbert	93.51	97.20	95.85	95.52
biomedbert-small-embeddings	93.25	97.93	96.65	95.94
biomedbert-hash-nano-colbert	90.45	96.81	92.00	93.09
biomedbert-hash-nano-embeddings	90.39	96.29	95.32	94.00
pubmedbert-base-embeddings	93.27	97.00	96.58	95.62

As with other ColBERT models on this dataset, it tends to score lower with longer form queries. But note how this model outperforms it's equivalent small model on the PubMed QA dataset. For traditional user queries, this model will likely get better results in production.

Full Model Architecture

ColBERT(
  (0): Transformer({'max_seq_length': 511, 'do_lower_case': False, 'architecture': 'BertModel'})
  (1): Dense({'in_features': 384, 'out_features': 128, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False})
)

More Information

Read more about the model in this article.