philcombiths / phonoerrorpatterns Goto Github PK
View Code? Open in Web Editor NEWIdentifies error patterns from phonological/phonetic transcriptions
License: Apache License 2.0
Identifies error patterns from phonological/phonetic transcriptions
License: Apache License 2.0
=========== Phono Error Patterns =========== Phono Error Patterns identifies error patterns from phonological transcriptions. Specifically, from IPA target and actual transcriptions, generates error pattern labels with error_pattern() for a single pair of transcriptions or error_pattern_table() for a dataset of transcription pairs. Note: Check function docstrings for valid phonological types. Note: This script uses panphon package. Typical usage:: # Example use case: result = error_patterns_table("...microdata_c.csv") # Debug Testing test_cases = import_test_cases() test_result = debug_testing(test_cases) Functions ========= error_pattern_resolver() takes a second pass through transcriptions with a more sophisticated algorithm to resolve patterns labelled with "_other". This may be a better algorithm to replace error_pattern() in future update. Currently only works as expected for CC substitution and epenthesis patterns. error_quantifier() may be used to convert error pattern str labels to numeric values. error_patterns_table uses these functions in sequence and exports result to csv. Panphon Setup Procedures ========= 1. Install or verify installation of panphon in the current python environment: e.g., 'pip install -e git+https://github.com/dmort27/panphon.git#egg=panphon' 2. Use extract_diacritics() to derive list of unique diacritics in dataset. - Requires transcriptions in a single column. 3. Update diacritic_definitions.yml in panphon/data with any diacritics not already in definitions. 4. Run command line from panphon directory to update definitions: 'python bin/generate_ipa_all.py data/ipa_bases.csv -d data/diacritic_definitions.yml -s data/sort_order.yml data/ipa_all.csv' 5. Copy 'ipa_all.csv' and paste into the panphon/data directory in the current python environment (e.g., 'C:/Users/Philip/Anaconda3/Lib/site-packages/panphon/data') David R. Mortensen, Patrick Littell, Akash Bharadwaj, Kartik Goyal, Chris Dyer, Lori Levin (2016). "PanPhon: A Resource for Mapping IPA Segments to Articulatory Feature Vectors." Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 3475â3484, Osaka, Japan, December 11-17 2016. Version ========= 0.1 License ======== Apache License 2.0 Copyright 2020 Philip Combiths
error_pattern_resolver() currently only works as expected for CC substitution and epenthesis patterns. Operations on dist_matrix will need to account for many more possible combinations when len target or actual > 2.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
đ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. đđđ
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google â¤ī¸ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.