Skip to main content

A library that provides a tool to edit model easily.

Project description

KGEditor

Code for our paper “Editing Language Model-based Knowledge Graph Embeddings”.

To use as a python module

pip install -kgeditor

Run the experiments

Training

Edit Task

To train the KGEditor model in the paper on the dataset E-FB15k237, run the command below. For another dataset E-WN18RR just replacing the dataset name will be fine.

./scripts/kgeditor_fb15k237_edit.sh

Add Task

To train the KGEditor model in the paper on the dataset A-FB15k237, run the command below. For another dataset A-WN18RR just replacing the dataset name will be fine.

./scripts/kgeditor_fb15k237_add.sh

Models

This folder contains the base models used for this work.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kgeditor-1.0.0.tar.gz (38.7 kB view details)

Uploaded Source

Built Distribution

kgeditor-1.0.0-py3-none-any.whl (41.5 kB view details)

Uploaded Python 3

File details

Details for the file kgeditor-1.0.0.tar.gz.

File metadata

  • Download URL: kgeditor-1.0.0.tar.gz
  • Upload date:
  • Size: 38.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.15

File hashes

Hashes for kgeditor-1.0.0.tar.gz
Algorithm Hash digest
SHA256 84c1f35e32487b505280d46a16550c6856cece2259620cd4648fbb13f74c1f1f
MD5 d1baf672d45515008fbcc26378f60bfe
BLAKE2b-256 ca427d5ae0111eed9d12a342c1ad7cbfa64060fecbcfebc92f3282c03dc862dd

See more details on using hashes here.

File details

Details for the file kgeditor-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: kgeditor-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 41.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.8.15

File hashes

Hashes for kgeditor-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d2fa62274b880f37b41716864e5a7cb9781547205f1f5d678ffd47709bc37ed2
MD5 6086a6892f15947810ec1087be0823d0
BLAKE2b-256 1f8350d8ccb328294851a98239e6efeae408dc46916b57d33dfe46e3186b23f0

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page