Comparing two trainable grammatical relations finders

TL;DR

This paper compares two trainable grammatical relations finders, revealing that their different learning techniques have minor effects and that GR length measures and data partitioning significantly influence performance.

Contribution

It provides a comparative analysis of two systems for grammatical relation finding, highlighting the impact of GR length measures and data partitioning.

Findings

Different GR length measures suit different GR types.

Partitioning data can improve memory-based learning.

Learning technique differences have minor effects.

Abstract

Grammatical relationships (GRs) form an important level of natural language processing, but different sets of GRs are useful for different purposes. Therefore, one may often only have time to obtain a small training corpus with the desired GR annotations. On such a small training corpus, we compare two systems. They use different learning techniques, but we find that this difference by itself only has a minor effect. A larger factor is that in English, a different GR length measure appears better suited for finding simple argument GRs than for finding modifier GRs. We also find that partitioning the data may help memory-based learning.