You are on page 1of 12

The Stanford Parser: Dependency Parser

Presented by
Chamara M. Dodandeniya

Reg No: Co.Sc/13/256


Intake : 30
Faculty : Faculty of
Computing

What is NLP Parser?


A natural language parser is a
program that works out the
grammatical structure of
sentences, for instance, which
groups of words go together (as
"phrases") and which words are the
subject or object of a verb.
Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

Stanford Parser
Develop by Sanford university.
It is java implementation tool kit.
Original parser mainly written by
Dan Klein

Christopher Manning

Roger Levy
Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

A dependency parser analyzes the


grammatical structure of a sentence,
establishing relationships between
"head" words and words which
modify those heads.

Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

How its works?


This parser builds a parse by performing
a linear-time scan over the words of a
sentence. At every step it maintains a
partial parse, a stack of words which are
currently being processed, and a buffer
of words yet to be processed.
The parser continues to apply transitions
to its state until its buffer is empty and
the dependency graph is completed.
Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

Stanford Parser Package


contents
PCFG and dependency parsers,
Lexicalized PCFG parser,
Super-fast neural-network
dependency parser
Deep learning reranker.

Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

How to use this tool?

Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

Advantages
Dependency parsing is easy to adapt to new
languages.
Well-adapted to representing free word-order.
It is preferred representation for many new
linguistic corpora.
Also developing in the direction of multilingual parsing where a single system is
required to be successful with different
language.
Can use this to building better NLP systems
Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

Demo

Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

Reference
[1] Nlp.stanford.edu, "The Stanford NLP (Natural Language Processing)
Group", 2016. [Online]. Available:
http://nlp.stanford.edu/software/index.shtml. [Accessed: 19- Jan- 2016]
[2] Nlp.stanford.edu, "The Stanford NLP (Natural Language Processing)
Group", 2016. [Online]. Available:
http://nlp.stanford.edu/software/nndep.shtml. [Accessed: 19- Jan- 2016]
[3] Nlp.stanford.edu, "The Stanford NLP (Natural Language Processing)
Group", 2016. [Online]. Available: http://nlp.stanford.edu/software/lexparser.shtml. [Accessed: 19- Jan- 2016]
[4] Chaoticity.com, "DependenSee: A Dependency Parse
Visualisation/Visualization Tool chaoticity", 2010. [Online]. Available:
http://chaoticity.com/dependensee-a-dependency-parse-visualisationtool/. [Accessed: 19- Jan- 2016]
[5] Wikipedia, "Dependency grammar", 2016. [Online]. Available:
https://en.wikipedia.org/wiki/Dependency_grammar. [Accessed: 19- Jan2016]

Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

Thank you

Reg No: Co.Sc/13/256

The Stanford Parser: Dependency Parser

You might also like