Parsing Natural Language Sentences by Semi-supervised Methods

TL;DR

This paper explores semi-supervised methods for natural language parsing, emphasizing cross-lingual transfer, annotation style effects, a new language similarity measure, and a novel parser combination technique.

Contribution

It introduces KLcpos3, a language similarity measure, and a resource interpolation method, advancing multi-source delexicalized parser transfer techniques.

Findings

Treebank annotation styles significantly affect parsing performance.

KLcpos3 effectively weights source parsers based on language similarity.

Interpolation of trained parser models improves transfer accuracy.

Abstract

We present our work on semi-supervised parsing of natural language sentences, focusing on multi-source crosslingual transfer of delexicalized dependency parsers. We first evaluate the influence of treebank annotation styles on parsing performance, focusing on adposition attachment style. Then, we present KLcpos3, an empirical language similarity measure, designed and tuned for source parser weighting in multi-source delexicalized parser transfer. And finally, we introduce a novel resource combination method, based on interpolation of trained parser models.