Skip to main content

Phonotactic generalization using recombination

Project description

Introduction

This library is meant to supplement the presentation Phonotactic well-formedness is recombinant, given at the 55th Annual Meeting of the SLE.

It learns typologically diverse phonotactics from positive examples alone.

Installation

pip install recombinant

Example

Here, we generalize the set /miememei, oumumo, momomu, iememi/ and then elicit ratings for /meem, memo, mumo/.

from recombinant import Learner

L = Learner([
    'miememei',
    'oumumo',
    'momomu',
    'iememi',
])

L.optimize()

print(L.rate('meem')) # => 0.4873949579831933 
print(L.rate('memo')) # => 0
print(L.rate('mumo')) # => 0.7899159663865546
print(L.basis)        # => ['momu', 'momo', 'oumo', 'memi', 'mi', 'emi', ...]

The actual learning takes place during the call to L.optimize(). Sometimes, running this optimization routine more than once gives better results.

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

recombinant-1.1.0.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

recombinant-1.1.0-py3-none-any.whl (5.6 kB view details)

Uploaded Python 3

File details

Details for the file recombinant-1.1.0.tar.gz.

File metadata

  • Download URL: recombinant-1.1.0.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.10.6

File hashes

Hashes for recombinant-1.1.0.tar.gz
Algorithm Hash digest
SHA256 eaee363c9178c258eed87c3685b6b166185a03c347f87d7daf7b215914387e93
MD5 ce19b74360ed7f8d82ae3f1426c922e7
BLAKE2b-256 1b860773471c7afab0b337d6f599d4d15b4153c34e2ffaddd7fec3e8faea77ae

See more details on using hashes here.

File details

Details for the file recombinant-1.1.0-py3-none-any.whl.

File metadata

  • Download URL: recombinant-1.1.0-py3-none-any.whl
  • Upload date:
  • Size: 5.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.10.6

File hashes

Hashes for recombinant-1.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 48f55e3a5a0162b448aa0982edd57f2b77145d08f90b4a39ca1df728dc693d3d
MD5 7eca4018d13271d8f6f34e9a6d8c161b
BLAKE2b-256 ef28551a71e2114ece0c9a6d1fcfa37b9f4bd3cecab17c1c68686e9a71ebe614

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