Introduction

DeSR is a dependency parser for natural language sentences.

Among its notable features:

• accuracy: close to state of the art accuracy
• efficiency: it can parse up to 200 sentence/sec
• multilingual: it can be trained from an annotated corpus on multiple languages
• customizable: features used in training can be customized.

Technique

DeSR is a shift-reduce dependency parser, which uses a variant of the approach of (Yamada and Matsumoto, 2003).

Dependency structures are built scanning the input from left to right and deciding at each step whether to perform a shift or to create a dependency between two adjacent tokens.

DeSR uses though a different set of rules and includes additional rules to handle non-projective dependencies that allow parsing to be performed deterministically in a single pass. The algorithm also produces fully labeled dependency trees.

A classifier is used for learning and predicting the proper parsing action. The parser can be configured, selecting among several learning algorithms (Averaged Perceptron, Maximum Entropy, memory-based learning using TiMBL, support vector machines using libSVM), providing user-defined feature models, and selecting input-output formats (including the CoNLL shared task format).

Training

Suppose you have both the parser and the configuration file in the same directory, you call:

   desr -t -m modelFile trainFile

to produce a model from a training corpus in CoNLL format.

Be careful using option SecondOrder, since it may considerably increase the model size.

Parsing

To parse sentences in CoNLL format, use:

   desr -m modelFile parseFile > parsedFile

If you plan to use the downloaded model file, first gunzip it.

For a full list of options, type:

   desr -h

Classifiers

Several classifiers are available, including: Maximum Entropy (-aME), Perceptron (-aAP), MBL (-aMBL) or SVM (-aSVM). The algorithm can also be specified in the configuration file desr.conf as well as the features to be used.

• Maximum Entropy classifier
• Averaged Perceptron
• SVM
• Memory Based Learning (requires optional library)
• SnOW (requires optional library)