Open source semantic parser: Google's SLING, SyntaxNet
SyntaxNet The world's most accurate natural language parser
SyntaxNet is a framework, also known as SyntacticParser in academic circles, which is a key component in many NLU systems. Enter a sentence in this system, and it will automatically mark each word in the sentence with POS (part-of-Speech) tags to describe the syntactic functions of these words and present them in the dependency syntax tree. These syntactic relations directly relate to the underlying meaning of the sentence.
- Source code
https://gitee.com/mirrors/syntaxnet
SLING - A natural language frame semantics parser
SLING is a parser for annotating text with frame semantic annotations. It is trained on an annotated corpus using Tensorflow and Dragnn.
The parser is a general transition-based frame semantic parser using bi-directional LSTMs for input encoding and a Transition Based Recurrent Unit (TBRU) for output decoding. It is a jointly trained model using only the text tokens as input and the transition system has been designed to output frame graphs directly without any intervening symbolic representation.
- Source code
https://gitee.com/little_fei/SLING/#parsing