Skip to main content

A lightweight library for entity linking in Greek.

Project description

Lightweight entity linking solution for Greek language.

Please consider citing our works if you use code from this repository. Also, we recommend using a Colab T4 GPU for faster results.

Main dependencies

  • python>=3.10
  • numpy==1.26.4
  • SPARQLWrapper==2.0.0
  • sentence_transformers==3.1.1
  • aiohttp==3.9.5
  • openai==1.55.3
  • httpx==0.27.2
  • beautifulsoup4==4.12.2
  • nest_asyncio==1.5.8

Example & Usage

from linking import main

# Your API token which can be found here (https://github.com/marketplace/models/azure-openai/gpt-4o)
api_token = "YOUR_API_TOKEN"

main.EL(api_token=api_token,
	sentence="Χάρη στην ΕΦΓ, μια μηχανή μπορεί να 'καταλάβει' το περιεχόμενο των εγγράφων, συμπεριλαμβανομένων των αποχρώσεων του πλαισίου των της γλώσσας σε αυτά.",
	mention="ΕΦΓ",
	single="No",
	combination="No",
	disambiguation="Yes",
	embedding_model="intfloat/multilingual-e5-large-instruct")
The correct entity for 'ΕΦΓ' is:

Wikipedia: https://el.wikipedia.org/wiki/Επεξεργασία_φυσικής_γλώσσας

Wikidata: https://www.wikidata.org/wiki/Q30642

DBpedia: http://dbpedia.org/resource/Natural_language_processing


Execution Time: 00:00:29

Parameters

  • api_token: Your API token from here. (Required)
  • sentence: A Greek text. (Required)
  • mention: The mention you want to perform the linking, the mention should be from inside the provided sentence. (Required)
  • disambiguation: Used when the mention has acronyms or the mention has two different entities inside (e.g. PCA and FA), (deafult="Yes"), (Values: "Yes", "No"). (Optional)
  • single: Usually used for difficult mentions, it searches each word of the mention individually, (deafult="No"), (Values: "Yes", "No"). (Optional)
  • combination: Usually used for difficult mentions, it makes combinations for each word of the mention, (deafult="No"), (Values: "Yes", "No"). (Optional)
  • embedding_model: A sentence-transformers model to perform text similarity, (deafault="intfloat/multilingual-e5-large-instruct"), (Values: str of the name of any sentence-transformers model that supports Greek). (Optional)

Licence

This library is licensed under the CC-BY-NC 4.0 license.

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

py_entity_linking_el-0.1.5.tar.gz (7.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

py_entity_linking_el-0.1.5-py3-none-any.whl (8.0 kB view details)

Uploaded Python 3

File details

Details for the file py_entity_linking_el-0.1.5.tar.gz.

File metadata

  • Download URL: py_entity_linking_el-0.1.5.tar.gz
  • Upload date:
  • Size: 7.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.1

File hashes

Hashes for py_entity_linking_el-0.1.5.tar.gz
Algorithm Hash digest
SHA256 7e08d2d3ac07e541ebf3932be9d6cbf606289b87102887598cf9f04952a4e6d2
MD5 315c2517405804cf78bd627c82355ba4
BLAKE2b-256 a50177ae3cd7cc6f8836bbad6be1ed91e0674c3a5bedf99dc0ab41217d459d76

See more details on using hashes here.

File details

Details for the file py_entity_linking_el-0.1.5-py3-none-any.whl.

File metadata

File hashes

Hashes for py_entity_linking_el-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 d4966e3d89834061ecf68e846fa46474947bc3b7b2f866440e8f5801becc0d22
MD5 8072ccd2792a7ca0e7eaf2f9d9ab5102
BLAKE2b-256 d4142764ab007935960c5ad089b610e46b118be736d37f537c3ac12c5881bc2f

See more details on using hashes here.

Supported by

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