Considering a resource-light approach to learning verb valencies

TL;DR

This paper explores a resource-light method for learning verb subcategorization frames in under-resourced, morphologically rich languages like Quechua, comparing minimal-resource approaches with more resource-intensive methods in Arabic.

Contribution

It demonstrates the limitations of minimal-resource approaches for complex verb learning and highlights the need for additional linguistic tools like POS taggers and chunkers.

Findings

Minimal-resource approach is insufficient for Arabic verb valency learning.

Additional tools improve the learning process.

Resource requirements vary across languages.

Abstract

Here we describe work on learning the subcategories of verbs in a morphologically rich language using only minimal linguistic resources. Our goal is to learn verb subcategorizations for Quechua, an under-resourced morphologically rich language, from an unannotated corpus. We compare results from applying this approach to an unannotated Arabic corpus with those achieved by processing the same text in treebank form. The original plan was to use only a morphological analyzer and an unannotated corpus, but experiments suggest that this approach by itself will not be effective for learning the combinatorial potential of Arabic verbs in general. The lower bound on resources for acquiring this information is somewhat higher, apparently requiring a a part-of-speech tagger and chunker for most languages, and a morphological disambiguater for Arabic.