MSTParser is a non-projective dependency parser that searches for maximum spanning trees over directed graphs. Models of dependency structure are based on large-margin discriminative training methods. Projective parsing is also supported.

mstparser 0.5.1 is now available via Maven Central. If you use Maven as your build tool, then you can add it as a dependency in your pom.xml file:

<dependency>
<groupId>net.sourceforge.mstparser</groupId>
<artifactId>mstparser</artifactId>
<version>0.5.1</version>
</dependency>

Features

  • First and second order projective and non projective parsing
  • Perceptron and k-best MIRA training
  • Edge-wise confidence estimation (as of v0.5.0)

Project Activity

See All Activity >

License

Apache License V2.0

Follow MSTParser

MSTParser Web Site

You Might Also Like
Discover Multiview ERP: The Financial Management Revolution Icon
Discover Multiview ERP: The Financial Management Revolution

Reclaim precious moments with loved ones while our robust cloud accounting software streamlines your financial processes.

Built for growing businesses and well-established enterprises alike, Multiview is a highly scalable and robust ERP.
Rate This Project
Login To Rate This Project

User Ratings

★★★★★
★★★★
★★★
★★
3
0
0
0
0
ease 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
features 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
design 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5
support 1 of 5 2 of 5 3 of 5 4 of 5 5 of 5 0 / 5

User Reviews

There are no 1 star reviews.

Additional Project Details

Intended Audience

Information Technology, Science/Research, Developers

User Interface

Command-line

Programming Language

Python, Java

Related Categories

Python Artificial Intelligence Software, Python HMI Software, Java Artificial Intelligence Software, Java HMI Software

Registered

2006-09-28