nlstruct 0.0.3.post1

Natural language structuring library

NLStruct

Natural language struturing library. Currently, it implements only a NER model, but other algorithms will follow.

Features

• processes large documents seamlessly: it automatically handles tokenization and sentence splitting.
• do not train twice: an automatic caching mechanism detects when an experiment has already been run
• stop & resume with checkpoints
• easy import and export of data
• handles nested or overlapping entities
• pretty logging with rich_logger
• heavily customizable, without config files (see train_ner.py)
• built on top of transformers and pytorch_lightning

How to train a NER model

from nlstruct.recipes import train_ner

model = train_ner(
    dataset={
        "train": "path to your train brat/standoff data",
        "val": 0.05,  # or path to your validation data
        # "test": # and optional path to your test data
    },
    finetune_bert=False,
    seed=42,
    bert_name="camembert/camembert-base",
    fasttext_file="",
    gpus=0,
    xp_name="my-xp",
)
model.save_pretrained("ner.pt")

How to use it

from nlstruct import load_pretrained
from nlstruct.datasets import load_from_brat, export_to_brat

ner = load_pretrained("ner.pt")
export_to_brat(ner.predict(load_from_brat("path/to/brat/test")), filename_prefix="path/to/exported_brat")

Status

This project is still under development and subject to changes.