DeepGrammar
is a grammar checker that integrates deep symbolic processing and
deep learning (artificial neural networks). It uses deep learning to
learn a model of language, and it then uses this model to check text
for errors in three steps:
- Compute
the likelihood that someone would have intended to write the text.
- Attempt
to generate text that is close to the written text but is more
likely.
- If
such text is found, show it to the user as a possible correction.
The
following page demonstrates a prototype of DeepGrammar.
No hay comentarios:
Publicar un comentario