Google today released on GitHub an English parser,
Parsey McParseface . From Google Research Blog —
"Today, we are excited to share the fruits of our research
with the broader community by releasing SyntaxNet,
an open-source neural network framework implemented in
TensorFlow that provides a foundation for
Natural Language Understanding (NLU) systems.
Our release includes all the code needed to train new
SyntaxNet models on your own data, as well as
Parsey McParseface , an English parser that we have
trained for you and that you can use to analyze English text."
"While the accuracy is not perfect, it’s certainly high enough
to be useful in many applications. The major source of errors
at this point are examples such as the prepositional phrase
attachment ambiguity described above, which require real
world knowledge (e.g. that a street is not likely to be located
in a car) and deep contextual reasoning. Machine learning
(and in particular, neural networks) have made significant
progress in resolving these ambiguities. But our work is still
cut out for us: we would like to develop methods that can
learn world knowledge and enable equal understanding of
natural language across all languages and contexts."
But seriously …
For some historical background, see (for instance) a book by
Ekaterina Ovchinnikova —
Integration of World Knowledge for
Natural Language Understanding ,
Atlantis Press, Springer, 2012.
A PDF of Chapter 2, "Natural Language Understanding
and World Knowledge," is available for download.
The philosophical background is the distinction between
syntax and semantics . See (for instance) …
