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)
License
Apache License V2.0Follow MSTParser
You Might Also Like
Our 360 recognition & rewards platform enables everyone (peer to peer & manager to employees alike) to send meaningful recognition rooted in core values. Nectar has the most extensive rewards catalog so users can choose from company branded swag, Amazon products, gift cards or custom reward types. Integrate with your other tools like Slack and Teams to make sending recognition easy. We support top organizations like MLB, SHRM, Redfin, Heineken and more.
Rate This Project
Login To Rate This Project
User Reviews
-
You can give me how to run MST Parser to generate k-best trees for one sentence (not the best tree as default). Many thanks!
-
Works well for me. Will use it again in the future.
-
A great application that is true to its promise. Thank you very much.