Considering a resource-light approach to learning verb valencies
This work addresses the challenge of verb valency learning for under-resourced languages, but it is incremental as it identifies limitations in existing minimal-resource methods.
The researchers tackled the problem of learning verb subcategorizations for under-resourced languages like Quechua and Arabic using minimal resources, but found that a resource-light approach with only a morphological analyzer and unannotated corpus was ineffective for Arabic, requiring additional tools like a part-of-speech tagger and chunker.
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.