Structural Ambiguity and its Disambiguation in Language Model Based Parsers: the Case of Dutch Clause Relativization
This addresses parsing accuracy for linguistically complex Dutch constructions, but is an incremental study comparing existing methods.
The paper tackles structural ambiguity in Dutch relative clauses by using prior sentence context for disambiguation, comparing two neural parsing architectures. Results show a neurosymbolic parser based on proof nets is more amenable to data bias correction than a universal dependencies approach, though both initially suffer from similar bias.
This paper addresses structural ambiguity in Dutch relative clauses. By investigating the task of disambiguation by grounding, we study how the presence of a prior sentence can resolve relative clause ambiguities. We apply this method to two parsing architectures in an attempt to demystify the parsing and language model components of two present-day neural parsers. Results show that a neurosymbolic parser, based on proof nets, is more open to data bias correction than an approach based on universal dependencies, although both setups suffer from a comparable initial data bias.