abydos
abydos copied to clipboard
chrislit
Abydos NLP/IR library for Python
`from abydos.stemmer import *` `ee = Porter2(early_english=True)` `ee.stem('Eest')`
https://github.com/chrislit/abydos/blob/a3715a0c0b63f4a127a622447a42624b812eb459/abydos/distance/_token_distance.py#L216 This isn't possible until DamerauLevenshtein can return an alignment (when the _alignment_matrix method is implemented).
Develop a normalized version of Millar().dist_abs()
Some of these might be duplicates or uninteresting.... - [ ] http://blclab.org/wp-content/uploads/2013/02/patpho.pdf - [ ] https://www.microsoft.com/en-us/research/blog/a-phonetic-matching-made-in%CB%88h%C9%9Bv%C9%99n/ - [ ] https://github.com/Microsoft/PhoneticMatching - [ ] https://cran.r-project.org/web/packages/stringdist/stringdist.pdf - [ ] https://journal.r-project.org/archive/2014-1/loo.pdf - [...
Ainsworth: 10.1109/TAU.1973.1162452 Ipadist: 10.1145/243199.243258
Cf. https://cran.r-project.org/web/packages/mclustcomp/mclustcomp.pdf Some of these measures are already implemented; others may not be useful or appropriate. But they should be examined & evaluated. - [ ] Adjusted Rand - [x]...
Candidates: - [x] Levenshtein/OSA - [ ] Damerau-Levenshtein - [x] Yujian-Bo - [ ] Higuera-Mico - [x] Indel - [ ] SAPS - [ ] Meta-Levenshtein - [ ] FlexMetric...
Add another intersection type: Fuzzy intersection based on ordered tokens, using Levenshtein alignments to parcel out the similarity weights: Given two aligned strings: - two equal tokens mean weight for...
These are things that were considered for implementation, but were not. Some don't make sense. Some looked too hard/impossible to implement or implement efficiently. They may be worth further consideration....