Skip to content

Latest commit

 

History

History
178 lines (103 loc) · 5.99 KB

README.md

File metadata and controls

178 lines (103 loc) · 5.99 KB
Raw

Constituency TreeBanks

When one talks about the “success” of a Natural Language Processing solution, they often refer to its ability to analyse the semantic and syntactic structure of a given sentence. Such a solution is expected to be able to understand both the linear and hierarchical order of the words in a sentence, unveil embedded structures, illustrate syntactical relationships and have a firm grasp of the argument structure. In order to meet the expectations, cutting edge Natural Language Processing systems like parsers, POS taggers or machine translation systems make use of syntactically or semantically annotated treebanks. Such treebanks offer a deep look through the surface and into the logical form of sentences.

Annotated treebanks can be categorised as constituency treebanks and dependency treebanks. Constituency treebanks offers clarity through resolving structural ambiguities, and successfully illustrates the syntagmatic relations like adjunct, complement, predicate, internal argument, external argument and such.

The very first comprehensive annotated treebank, the Penn Treebank, was created for the English language and offers 40,000 annotated sentences. Following the Penn Treebank, numerous treebanks annotated for constituency structures were developed in different languages including French, German, Finnish, Hungarian, Chinese and Arabic.

Video Lectures

Class Diagram

For Developers

You can also see Python, Cython, C, C++, Swift, Js, or C# repository.

Requirements

Java

To check if you have a compatible version of Java installed, use the following command:

java -version

If you don't have a compatible version, you can download either Oracle JDK or OpenJDK

Maven

To check if you have Maven installed, use the following command:

mvn --version

To install Maven, you can follow the instructions here.

Git

Install the latest version of Git.

Download Code

In order to work on code, create a fork from GitHub page. Use Git for cloning the code to your local or below line for Ubuntu:

git clone <your-fork-git-link>

A directory called ParseTree will be created. Or you can use below link for exploring the code:

git clone https://github.com/olcaytaner/ParseTree.git

Open project with IntelliJ IDEA

Steps for opening the cloned project:

  • Start IDE
  • Select File | Open from main menu
  • Choose ParseTree/pom.xml file
  • Select open as project option
  • Couple of seconds, dependencies with Maven will be downloaded.

Compile

From IDE

After being done with the downloading and Maven indexing, select Build Project option from Build menu. After compilation process, user can run ParseTree.

From Console

Go to ParseTree directory and compile with

 mvn compile

Generating jar files

From IDE

Use package of 'Lifecycle' from maven window on the right and from ParseTree root module.

From Console

Use below line to generate jar file:

 mvn install

Maven Usage

    <dependency>
        <groupId>io.github.starlangsoftware</groupId>
        <artifactId>ParseTree</artifactId>
        <version>1.0.15</version>
    </dependency>

Detailed Description

TreeBank

To load a TreeBank composed of saved ParseTrees from a folder:

TreeBank(File folder)

To load trees with a specified pattern from a folder of trees:

TreeBank(File folder, String pattern)

To load trees with a specified pattern and within a specified range of numbers from a folder of trees:

TreeBank(File folder, String pattern, int from, int to)

the line above is used. For example,

a = TreeBank(new File("/mypath"));

the line below is used to load trees under the folder "mypath" which is under the current folder. If only the trees with ".train" extension under the same folder are to be loaded:

a = TreeBank(new File("/mypath"), ".train");

If among those trees, only the ones between 1 and 500 are to be loaded:

a = TreeBank(new File("/mypath"), ".train", 1, 500);

the line below is used.

To iterate over the trees after the TreeBank is loaded:

for (int i = 0; i < a.size(); i++){
	ParseTree p = a.get(i);
}

a block of code like this can be useful.

ParseTree

To load a saved ParseTree:

ParseTree(FileInputStream file)

is used. Usually it is more useful to load a TreeBank as explained above than loading the ParseTree one by one.

To find the node number of a ParseTree:

int nodeCount()

leaf number of a ParseTree:

int leafCount()

number of words in a ParseTree:

int wordCount(boolean excludeStopWords)

above methods can be used.

Cite

@INPROCEEDINGS{9259873,
author={N. {Kara} and B. {Marşan} and M. {Özçelik} and B. N. {Arıcan} and A. {Kuzgun} and N. {Cesur} and D. B. {Aslan} and O. T. {Yıldız}},
booktitle={2020 Innovations in Intelligent Systems and Applications Conference (ASYU)}, 
title={Creating A Syntactically Felicitous Constituency Treebank For Turkish}, 
year={2020},
volume={},
number={},
pages={1-6},
doi={10.1109/ASYU50717.2020.9259873}}