Hierarchy Transformers (HiTs)

Hierarchy Transformers (HiTs) are capable of interpreting and encoding hierarchies explicitly.

The relevant code in HierarchyTransformers extends from Sentence-Transformers.

Get Started

Install hierarchy_tranformers (check our repository) through pip or GitHub.

Use the following code to get started with HiTs:

from hierarchy_transformers import HierarchyTransformer
from hierarchy_transformers.utils import get_torch_device

# set up the device (use cpu if no gpu found)
gpu_id = 0
device = get_torch_device(gpu_id)

# load the model
model = HierarchyTransformer.load_pretrained('Hierarchy-Transformers/HiT-MiniLM-L12-WordNet', device)

# entity names to be encoded.
entity_names = ["computer", "personal computer", "fruit", "berry"]

# get the entity embeddings
entity_embeddings = model.encode(entity_names)

Models

See available HiT models under this organisation.

Datasets

The datasets for training and evaluating HiTs are available at Zenodo.

Citation

Preprint on arxiv: https://arxiv.org/abs/2401.11374.

Yuan He, Zhangdie Yuan, Jiaoyan Chen, Ian Horrocks. Language Models as Hierarchy Encoders. arXiv preprint arXiv:2401.11374 (2024).

@article{he2024language,
  title={Language Models as Hierarchy Encoders},
  author={He, Yuan and Yuan, Zhangdie and Chen, Jiaoyan and Horrocks, Ian},
  journal={arXiv preprint arXiv:2401.11374},
  year={2024}
}