Claire Brierley

ProPOSEL: a human-oriented prosody and PoS English lexicon for machine-learning and NLP

ProPOSEL is a prosody and PoS English lexicon, purpose-built to integrate and leverage domain knowledge from several well-established lexical resources for machine learning and NLP applications. The lexicon of 104049 separate entries is in accessible text file format, is human and machine-readable, and is intended for open source distribution with the Natural Language ToolKit. It is therefore supported by Python software tools which transform ProPOSEL into a Python dictionary or associative array of linguistic concepts mapped to compound lookup keys. Users can also conduct searches on a subset of the lexicon and access entries by word class, phonetic transcription, syllable count and lexical stress pattern. ProPOSEL caters for a range of different cognitive aspects of the lexicon©.