README.md

metadata

license: apache-2.0
base_model:
  - meta-llama/Meta-Llama-3-8B-Instruct
language:
  - fr
tags:
  - BEL
  - retrieval
  - entity-retrieval
  - named-entity-disambiguation
  - entity-disambiguation
  - named-entity-linking
  - entity-linking
  - text2text-generation
  - biomedical
  - healthcare
  - synthetic-data
  - causal-lm
  - llm
library_name: transformers
finetuning_task:
  - text2text-generation
  - entity-linking
metrics:
  - recall
model-index:
  - name: syncabel-quaero-emea-8b
    results:
      - task:
          type: entity-linking
        dataset:
          type: structured_dataset
          name: bigbio/quaero
          config: quaero_emea_bigbio_kb
        metrics:
          - type: recall
            value: 0.79

SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking

SynCABEL

SynCABEL is a novel framework that addresses data scarcity in biomedical entity linking through synthetic data generation. The method, introduced in our [paper]

SynCABEL (QUAERO-EMEA Edition)

This is a finetuned version of LLaMA-3-8B trained on QUAERO-EMEA using SynthQUAERO (our synthetic dataset generated via the SynCABEL framework).

Base Model	meta-llama/Meta-Llama-3-8B-Instruct
Training Data	QUAERO-EMEA (real) + SynthQUAERO (synthetic)
Fine-tuning	Supervised Fine-Tuning

Training Data Composition

The model is trained on a mix of human-annotated and synthetic data:

QUAERO-EMEA (human)   : 7,159 mentions
SynthQUAERO (synthetic)  : 396,914 mentions

To ensure balanced learning, human data is upsampled during training so that each batch contains:

50% human-annotated data
50% synthetic data

In other words, although SynthMM is larger, the model always sees a 1:1 ratio of human to synthetic examples, preventing synthetic data from overwhelming human supervision.

Usage

Loading

import torch
from transformers import AutoModelForCausalLM

# Load the model (requires trust_remote_code for custom architecture)
model = AutoModelForCausalLM.from_pretrained(
    "AnonymousARR42/SynCABEL_QUAERO_EMEA",
    trust_remote_code=True,
    device_map="auto"
)

Unconstrained Generation

# Let the model freely generate concept names
sentences = [
    "Le patient atteint de [Embolie pulmonaire massive]{Disorders} a présenté des signes de détresse respiratoire.",
    "Le patient reçoit régulièrement des [corticoïdes]{Chemicals & Drugs} pour soulager les symptômes cutanés."
]

results = model.sample(
    sentences=sentences,
    constrained=False,
    num_beams=2,
)

for i, beam_results in enumerate(results):
    print(f"Input: {sentences[i]}")

    mention = beam_results[0]["mention"]
    print(f"Mention: {mention}")

    for j, result in enumerate(beam_results):
        print(
            f"Beam {j+1}:\n"
            f"Predicted concept name:{result['pred_concept_name']}\n"
            f"Predicted code: {result['pred_concept_code']}\n"
            f"Beam score: {result['beam_score']:.3f}\n"
        )

Output:

Input: Le patient atteint de [Embolie pulmonaire massive]{Disorders} a présenté des signes de détresse respiratoire.
Mention: Embolie pulmonaire massive
Beam 1:
Predicted concept name:Embolie pulmonaire massive
Predicted code: NO_CODE
Beam score: 0.820

Beam 2:
Predicted concept name:Grade 5 Pulmonary embolus
Predicted code: NO_CODE
Beam score: 0.709

Input: Le patient reçoit régulièrement des [corticoïdes]{Chemicals & Drugs} pour soulager les symptômes cutanés.
Mention: corticoïdes
Beam 1:
Predicted concept name:Corticoïdes
Predicted code: C0001617
Beam score: 0.941

Beam 2:
Predicted concept name:Corticosteroid
Predicted code: NO_CODE
Beam score: 0.520

Constrained Decoding (Recommended for Entity Linking)

# Constrained to valid biomedical concepts
sentences = [
    "Le patient atteint de [Embolie pulmonaire massive]{Disorders} a présenté des signes de détresse respiratoire.",
    "Le patient reçoit régulièrement des [corticoïdes]{Chemicals & Drugs} pour soulager les symptômes cutanés."
]

results = model.sample(
    sentences=sentences,
    constrained=True,
    num_beams=2,
)

for i, beam_results in enumerate(results):
    print(f"Input: {sentences[i]}")

    mention = beam_results[0]["mention"]
    print(f"Mention: {mention}")

    for j, result in enumerate(beam_results):
        print(
            f"Beam {j+1}:\n"
            f"Predicted concept name:{result['pred_concept_name']}\n"
            f"Predicted code: {result['pred_concept_code']}\n"
            f"Beam score: {result['beam_score']:.3f}\n"
        )

Output:

Input: Le patient atteint de [Embolie pulmonaire massive]{Disorders} a présenté des signes de détresse respiratoire.
Mention: Embolie pulmonaire massive
Beam 1:
Predicted concept name:Embolie pulmonaire massive aiguë
Predicted code: C0340535
Beam score: 0.460

Beam 2:
Predicted concept name:Embolie pulmonaire
Predicted code: C0034065
Beam score: 0.267

Input: Le patient reçoit régulièrement des [corticoïdes]{Chemicals & Drugs} pour soulager les symptômes cutanés.
Mention: corticoïdes
Beam 1:
Predicted concept name:Corticoïdes
Predicted code: C0001617
Beam score: 0.941

Beam 2:
Predicted concept name:Corticosteroid therapy
Predicted code: C1313874
Beam score: 0.320

Scores

Entity linking performance (Recall@1) on biomedical benchmarks. The best results are shown in bold, the second-best results are underlined, and the "Average" column reports the mean score across the four benchmarks.

Model	MM-ST21PV (english)	QUAERO-MEDLINE (french)	QUAERO-EMEA (french)	SPACCC (spanish)	Avg.
SciSpacy	53.8	40.5	37.1	13.2	36.2
SapBERT	51.1	50.6	49.8	33.9	46.4
CODER-all	56.6	58.7	58.1	43.7	54.3
SapBERT-all	64.6	74.7	67.9	47.9	63.8
ArboEL	74.5	70.9	62.8	49.0	64.2
mBART-large	65.5	61.5	58.6	57.7	60.8
+ Guided inference	70.0	72.8	71.1	61.8	68.9
+ SynCABEL (Our method)	71.5	77.1	75.3	64.0	72.0
Llama-3-8B	69.0	66.4	65.5	59.9	65.2
+ Guided inference	74.4	77.5	72.9	64.2	72.3
+ SynCABEL (Our method)	75.4	79.7	79.0	67.0	75.3

Here, we provide the source repositories for the baselines:

• SciSpacy
• SapBERT
• SapBERT-all
• CODER-all
• ArboEL
• mBART-large
• LLaMA-3-8B.

Speed and Memory

Model	Model (GB)	Cand. (GB)	Speed (/s)
SapBERT	2.1	20.1	575.5
ArboEL	1.2	7.1	38.9
mBART	2.3	5.4	51.0
Llama-3-8B	28.6	5.4	19.1

Measured on single H100 GPU, constrained decoding