Natural Language Syntactic Parsing System
(Redirected from natural language parser)
Jump to navigation
Jump to search
A natural language syntactic parsing system is a parsing system that implements linguistic syntactic parsing algorithm to solve a linguistic syntactic parsing task.
- AKA: Linguistic Parser, Syntactic Parser, Natural Language Parsing System.
- Context:
- It can range from being a Probabilistic Linguistic Syntactic Parser to being a Formal Linguistic Syntactic Parser.
- It can range from being a Linguistic Parsing Tree Parser to being a Linguistic Dependency Tree Parser.
- It can range from being a Human Linguistic Syntax Annotator (for the Penn Treebank project) to being an Automated Natural Language Syntactic Parser (such as a supervised linguistic syntactic parsing algorithm).
- It can be supported by Natural Language TEC System.
- Example(s):
- Counter-Example(s):
- a Natural Language Semantic Parsing System,
- a Computer Program Syntactic Parsing System,
- a WikiText Parsing System,
- a POS Tagger, such as a Stanford POS Tagger.
- an NER System, such as a LingPipe NER System.
- an SRL System, such as a SwiRL System.
- See: Natural Language Grammar, Natural Language Syntactic Accepter, Natural Language Processing System, Natural Language Generation System, Syntax Analysis.
References
2010
- http://www.nltk.org/book/ch08.html
- QUOTE: The goal of this chapter is to answer the following questions:
- How can we use a formal grammar to describe the structure of an unlimited set of sentences?
- How do we represent the structure of sentences using syntax trees?
- How do parsers analyze a sentence and automatically build a syntax tree?
- QUOTE: The goal of this chapter is to answer the following questions:
2009
- http://www.cse.unsw.edu.au/~billw/nlpdict.html#parser
- QUOTE: A parser is an algorithm (or a program that implements that algorithm) that takes a grammar, a and a string of words, decides whether the string of words can be derived from the grammar and lexicon (i.e. is a sentence with respect to the grammar and lexicon.
If so, it produces as output some kind of representation of the way (or ways) in which the sentence can be derived from the grammar and lexicon. A common way of doing this is to output (a) parse tree(s).
- QUOTE: A parser is an algorithm (or a program that implements that algorithm) that takes a grammar, a and a string of words, decides whether the string of words can be derived from the grammar and lexicon (i.e. is a sentence with respect to the grammar and lexicon.
1989
- (Abney, 1989) ⇒ Steven P. Abney. (1989). “Parsing By Chunks.” In: The MIT Parsing Volume, 1988-89. Center for Cognitive Science, MIT.
- QUOTE: … A typical natural language parser processes text in two stages. A tokenizer/morphological analyzer converts a stream of characters into a stream of words, and the parser proper converts a stream of words into a parsed sentence, or a stream of parsed sentences. In a chunking parser, the syntactic analyzer is decomposed into two separate stages, which I call the chunker and the attacher. The chunker converts a stream of words into a stream of chunks, and the attacher converts the stream of chunks into a stream of sentences.