Skip to main content

Pyramids Parser: English Language Semantic Extraction

Project description

English Language Semantic Extraction

Copyright (c) Aaron Hosford 2011-2015

Available under the MIT License

Pyramids gets its name from the way it constructs parse trees, working upwards from the leaves towards the root, building up layers of progressively smaller size but greater scope. It is a rule-based natural language parser, tailored specifically for English, which builds multiple competing parses for a sentence from the bottom up using principles of dynamic programming. The parses are then scored for quality and presented in order of descending rank. The parser is also capable of accepting feedback as to which parses are or are not acceptable, adaptively adjusting its scoring measures to improve future parse quality and ranking. Parses are returned as trees but can also be used to generate graphs representing the semantic relationships between words. The syntactic rules of the parser can also be run in reverse to generate sentences from semantic graphs resembling those it produces.

Project details


Download files

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

Files for pyramids, version 0.0.1
Filename, size File type Python version Upload date Hashes
Filename, size pyramids-0.0.1-py3-none-any.whl (423.0 kB) File type Wheel Python version py3 Upload date Hashes View
Filename, size pyramids-0.0.1.zip (378.8 kB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page