Transition-Based Dependency Parsing With Pluggable Classifiers

TL;DR

This paper extends MaltParser to seamlessly incorporate any classifier compatible with Weka, enabling flexible experimentation with classifiers like SVMs and memory-based learners in multilingual dependency parsing.

Contribution

It introduces a pluggable interface for classifiers in MaltParser, facilitating easy integration and comparison of different machine learning models for dependency parsing.

Findings

Support-vector machines outperform memory-based learners in parsing accuracy.

Memory-based learners do not perform better in low-resource scenarios as previously hypothesized.

Extensions enable flexible classifier experimentation in multilingual dependency parsing.

Abstract

In principle, the design of transition-based dependency parsers makes it possible to experiment with any general-purpose classifier without other changes to the parsing algorithm. In practice, however, it often takes substantial software engineering to bridge between the different representations used by two software packages. Here we present extensions to MaltParser that allow the drop-in use of any classifier conforming to the interface of the Weka machine learning package, a wrapper for the TiMBL memory-based learner to this interface, and experiments on multilingual dependency parsing with a variety of classifiers. While earlier work had suggested that memory-based learners might be a good choice for low-resource parsing scenarios, we cannot support that hypothesis in this work. We observed that support-vector machines give better parsing performance than the memory-based learner, regardless of the size of the training set.