Google has been promoting natural language understanding with the open-sourcing of SyntaxNet, a neural network framework, and Parsey McParseface. This interesting information came to us from DATAVERSITY in their article, “Google Promotes Natural Language Understanding with Open Source Projects.”
Parsey McParseface is more than just a cute moniker; it is built on machine learning algorithms that learn to analyze the structure of language and can explain the functional role of each word in a given sentence.
Implemented in Google’s open source TensorFlow machine intelligence library, SyntaxNet provides the code needed to train natural language understanding models on data along with Parsey McParseface.
Parsing is difficult for computers due to the ambiguity of human languages. A moderate-length sentence of 20 to 30 words could have as many as tens of thousands of possible syntactic structures. Thus far, Parsey McParseface has some impressive performance statistics.
Melody K. Smith
Sponsored by Access Innovations, the world leader in indexing and making content findable.