Spellcheck Network - Githubissues

Klebert-Engineering / deep-spell-9

Neural Spellcheck, Autocomplete and Fuzzy-match for SQLite FTS5 🤖

MIT License

2 stars 0 forks source link

Closed josephbirkner closed 6 years ago

josephbirkner commented 7 years ago

Research options for neural spelling correction OR error-labeling.

josephbirkner commented 7 years ago

Planned Architecture:

Variational Recurrent Auto-Encoder (VRAE) that learns to map incorrectly spelled tokens to correctly spelled ones by creating an intermediate low-dimensional hash.
The correction suggestion would come out of a k-Nearest-Neighbor search with the intermediate hash representation.
Such a representation could, for example, be 8xfloat16 per token.
This will also require corruption rules in the training grammar.

josephbirkner commented 7 years ago

~~Good implementation of VRAE in Tensor Flow that could be used as a drop-in RNNCell: https://github.com/kimkilho/tensorflow-vrnn~~

josephbirkner commented 6 years ago

849cdbf Issues #27 and #28 remain.