Skip to main content

Le's Lesk

A fast Python 3 Word-Sense Disambiguation package (WSD) using the extended LESK algorithm

Install

lelesk is available on PyPI and can be installed using pip

pip install lelesk

Lelesk uses NLTK lemmatizer and yawlib wordnet API. To install NLTK data, start a Python prompt, import nltk and then download the required data

$ python3
Python 3.6.9 (default, Jan 26 2021, 15:33:00) 
[GCC 8.4.0] on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import nltk
>>> nltk.download(['stopwords', 'punkt', 'averaged_perceptron_tagger', 'wordnet'])

Download and extract yawlib pre-built databases to ~/wordnet.

For more information:

Command-line tools

To disambiguate a sentence, run this command on the terminal:

python3 -m lelesk wsd "I go to the bank to get money."

To perform word-sense disambiguation on a text file, prepare a text file with each line is a sentence.

For example here is the content of the file demo.txt

I go to the bank to withdraw money.
I sat at the river bank.

you then can run the following command

# output to TTL/JSON (a single file)
python3 -m lelesk file demo.txt demo_wsd_output.json --ttl json

# output to TTL/TSV (multiple TSV files)
python3 -m lelesk file demo.txt demo_wsd_output.json --ttl tsv

Issues

If you have any issue, please report at https://github.com/letuananh/lelesk/issues

Download files

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

Source Distribution

lelesk-0.1.tar.gz (15.3 kB view details)

Uploaded Source

File details

Details for the file lelesk-0.1.tar.gz.

File metadata

  • Download URL: lelesk-0.1.tar.gz
  • Upload date:
  • Size: 15.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.6.9

File hashes

Hashes for lelesk-0.1.tar.gz
Algorithm Hash digest
SHA256 bf45ae30f9b39232def0aaf4a620d855667452cb12e4a1c69007d667b73c76a8
MD5 a2e9334fdec5e59ea09b12aa1d439638
BLAKE2b-256 f761397f475c65557b82aaf725e9e5724eeb38208fa1b44d925c9482e5946617

See more details on using hashes here.

Release history Release notifications | RSS feed

This release

0.1 This release

1 file

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page