logitorch 0.0.1a1

LogiTorch is a pytorch-based library for logical reasoning in natural language

LogiTorch

LogiTorch is a PyTorch-based library for logical reasoning in natural language, it consists of:

• Textual logical reasoning datasets
• Implementations of different logical reasoning neural architectures
• A simple and clean API that can be used with PyTorch Lightning

📦 Installation

foo@bar:~$ pip install logitorch

📖 Documentation

You can find the documentation for LogiTorch on ReadTheDocs.

🖥️ Features

📋 Datasets

Datasets implemented in LogiTorch:

• AR-LSAT
• ConTRoL
• LogiQA
• ReClor
• RuleTaker
• ProofWriter
• SNLI
• MultiNLI
• RTE
• Negated SNLI
• Negated MultiNLI
• Negated RTE
• PARARULES Plus
• AbductionRules

🤖 Models

Models implemented in LogiTorch:

• RuleTaker
• ProofWriter
• BERTNOT
• PRover
• FaiRR
• LReasoner
• DAGN
• Focal Reasoner
• AdaLoGN
• Logiformer
• LogiGAN

🧪 Example Usage

Training Example

import pytorch_lightning as pl
from logitorch.data_collators.ruletaker_collator import RuleTakerCollator
from logitorch.datasets.qa.ruletaker_dataset import RuleTakerDataset
from logitorch.pl_models.ruletaker import PLRuleTaker
from pytorch_lightning.callbacks import ModelCheckpoint
from torch.utils.data.dataloader import DataLoader

train_dataset = RuleTakerDataset("depth-5", "train")
val_dataset = RuleTakerDataset("depth-5", "val")

ruletaker_collate_fn = RuleTakerCollator()
train_dataloader = DataLoader(
    train_dataset, batch_size=32, collate_fn=ruletaker_collate_fn
)

val_dataloader = DataLoader(
    train_dataset, batch_size=32, collate_fn=ruletaker_collate_fn
)

model = PLRuleTaker(learning_rate=1e-5, weight_decay=0.1)

checkpoint_callback = ModelCheckpoint(
    save_top_k=1,
    monitor="val_loss",
    mode="min",
    dirpath="models/",
    filename="best_ruletaker",
)

trainer = pl.Trainer(accelerator="gpu", gpus=1)
trainer.fit(model, train_dataloader, val_dataloader)

Testing Example

from logitorch.pl_models.ruletaker import PLRuleTaker
from logitorch.datasets.qa.ruletaker_dataset import RULETAKER_ID_TO_LABEL
import pytorch_lightning as pl

model = PLRuleTaker.load_from_checkpoint("best_ruletaker.ckpt")

context = "Bob is smart. If someone is smart then he is kind"
question = "Bob is kind"

pred = model.predict(context, question)
print(RULETAKER_ID_TO_LABEL[pred])

Ethical Consideration

Users of LogiTorch should distinguish the datasets and models of our library from the originals. They should always credit and cite both our library and the original data source, as in ``We used LogiTorch's (citation) re-implementation of BERTNOT \cite{hosseini2021understanding}''.