license: cc0-1.0
datasets:
- empathyai/books-ner-dataset
language:
- en
base_model:
- gliner-community/gliner_large-v2.5
pipeline_tag: token-classification
library_name: gliner
tags:
- ner
- gliner
- books
- titles
- authors
Books Named Entity Recognition Model
This model specialises in recognising book titles and author names in short, user‑typed queries. It achieves > 92 % F1 on a held‑out evaluation set.
Check out this model in action in this experience!
1 Provenance
This model's provenance originates from fine-tuning gliner-community/gliner_large‑v2.5 using synthetic query data derived from Project Gutenberg's public catalogue.
2 Use‑case
This model is a drop‑in replacement for generic GLiNER when your text stream revolves around bibliographic requests such as:
“Looking for Dune from Frank Herbert.”
“Any recommendations by Mary Shelley?”
Typical applications:
- Query understanding in library / e‑book search engines
- Post‑processing LLM output to structure reading lists
- Digital humanities pipelines that need lightweight title/author extraction
Not suitable for: recognising publishers, ISBNs or long BIB‑style references (only short queries were used for training).
3 Performance
| Metric | Overall | title |
author |
|---|---|---|---|
| Precision | 0.9999 | 0.9999 | 0.9999 |
| Recall | 0.8583 | 0.7661 | 0.9287 |
| F1‑score | 0.9237 | 0.8675 | 0.9630 |
| Support | 69 880 | 30 290 | 39 590 |
Evaluation dataset: 43 493 queries (English‑only) held out from the training corpus. Prediction threshold = 0.2.
4 Quick start
from gliner import GLiNER
model = GLiNER.from_pretrained("empathyai/gliner_large-v2.5-books")
text = "Looking for The Man in the High Castle by Philip K. Dick."
entities = model.predict_entities(text, ["title", "author"], threshold=0.2)
print(entities)
# [{'text': 'The Man in the High Castle', 'label': 'title', 'score': 0.99},
# {'text': 'Philip K. Dick', 'label': 'author', 'score': 0.99}]
5 Training details
- Base model:
gliner_large-v2.5(≈ 459 M parameters, Creative Commons Zero v1.0 Universal) - Dataset:
empathyai/books-ner-dataset— 435 k synthetic English queries (titles + authors only) - Splits: 391 432 train / 43 493 eval (duplicates removed)
- Script highlights
- Learning rate 5 × 10⁻⁶, linear schedule, warm‑up 10 %
- Batch 32, gradient accumulation 2, focal loss α 0.75 / γ 2
- 1 epoch
- Gradient checkpointing + BF16 for memory efficiency
- Trained on a single L40S; total wall time ≈ 40 min
6 Limitations & bias
- The vocabulary of titles/authors comes from Project Gutenberg (public‑domain heavy; modern best‑sellers may be unseen).
- Only short, informal English queries were simulated. Long paragraphs or non‑English text may degrade accuracy.
- Does not tag publishers, dates, ISBNs, or other bibliographic fields.
7 Acknowledgements
Thanks to the GLiNER authors and maintainers; HuggingFace for hosting; Project Gutenberg volunteers for the free metadata.