# RBGParser

**Repository Path**: mirrors_allenai/RBGParser

## Basic Information

- **Project Name**: RBGParser
- **Description**: Graph-based Dependency Parser
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: new_label
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-09-24
- **Last Updated**: 2026-02-14

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README


### RBGParser v1.1

This version improves parsing speed using the hash kernel (see [4]) and by optimizing the code. We also improved the unlabeled attachment score (UAS) slightly and labeled attachment score (LAS) significantly. 

<br>
#### [Quick Start](https://github.com/taolei87/RBGParser/wiki/Quick-Start)

<br>
#### [FAQs](https://github.com/taolei87/RBGParser/wiki/FAQs)

======

#### About and Contact

This project is developed at Natural Language Processing group in MIT. It contains a Java implementation of a syntactic dependency parser with tensor decomposition and greedy decoding, described in [1,2,3].

This project is implemented by Tao Lei (taolei [at] csail.mit.edu) and Yuan Zhang (yuanzh [at] csail.mit.edu).

=========

#### References

[1] Tao Lei, Yu Xin, Yuan Zhang, Regina Barzilay and Tommi Jaakkola. Low-Rank Tensors for Scoring Dependency Structures.  ACL 2014. [PDF](http://people.csail.mit.edu/taolei/papers/acl2014.pdf)

[2] Yuan Zhang, Tao Lei, Regina Barzilay, Tommi Jaakkola and Amir Globerson. Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees.  ACL 2014. [PDF](http://people.csail.mit.edu/yuanzh/papers/acl2014.pdf)

[3] Yuan Zhang\*, Tao Lei\*, Regina Barzilay and Tommi Jaakkola. Greed is Good if Randomized: New Inference for Dependency Parsing. EMNLP 2014. [PDF](http://people.csail.mit.edu/taolei/papers/emnlp2014.pdf)

[4] Bernd Bohnet. Very High Accuracy and Fast Dependency Parsing is not a Contradiction. The 23rd International Conference on Computational Linguistics. COLING 2010. [PDF](http://anthology.aclweb.org/C/C10/C10-1011.pdf)