Damien Daspit
Damien Daspit
Currently, Thot has support for IBM1, IBM2, and HMM models, none of which models fertility. Are there any plans to support IBM3, IBM4, IBM5, or one of the extensions to...
Currently, when importing word lists, Cog always overwrites the existing word list data. It would be useful to allow a user to choose if they would like to overwrite or...
LexStat is a statistical algorithm for detecting cognates. It would be good to add this as another cognate identification method. It is implemented in the LingPy library. List, J.-M. (2012)....
Cog currently supports prefixes and suffixes in the stemming tool. It would be useful for Cog to support infixes as well.
Currently, Cog has the ability to align words from the beginning. There are some languages where the beginning of the word is unstable or has prefixes. To support these languages,...
The stemmer should not override words that have been manually stemmed by the user. The stemmer should skip over these words.
Currently, any specified similar segments apply to all variety pairs in a Cog project. Some users would like to have more fine-grained control of this, so they can specify which...
The alignment algorithm implementation in Cog does not currently support metathesis. Although rare, there are some instances of metathesis as a sound change.
Cog currently only supports V (vowel), C (consonant), and # (word-initial or word-final) in the environment of a segment in a similar or ignored correspondence. It would be useful if...
Here is the request from Wyn Owen: "Say I specified 20 similar segments, could Cog count the number of these that were used in a particular comparison, eg 15 out...