Difference between revisions of "User:Francis Tyers/Apertium 4"
Jump to navigation
Jump to search
Line 29: | Line 29: | ||
* Better treatment of "no-translate" |
* Better treatment of "no-translate" |
||
* User dictionaries |
* User dictionaries |
||
* Better handling of code-switching/mixed texts and informal text. |
Revision as of 20:03, 21 June 2020
Wish list for Apertium 4:
Software engineering
- Make the different parts of the engine code more coherent in terms of modules
Linguistic data
- Extract multiwords from lexicons into "separable" FSTs
- Train taggers for all languages
- At least one state-of-the-art language pair (wrt. Google).
Engine
- Use embeddings for morphological disambiguation and lexical selection
- Pass the surface form until transfer (to allow modules to look up surface form embeddings)
- Retire the HMM tagger
- Be able to train weights for morph analysis + morph. disambiguation + lexical selection + transfer end to end.
- Fully functional recursive transfer
- Neural system
- There should be a basic NMT implementation that functions in the Apertium ecosystem (C++,autotools,bash,apy,html-tools) for communities that want to build their own NMT systems and still take advantage of our ecosystem. We should be a one-stop shop for MT for marginalised langs.
End user
- Format handling
- Better treatment of "no-translate"
- User dictionaries
- Better handling of code-switching/mixed texts and informal text.