Constituents Correspond to Word Sequence Patterns among Sentences with Equivalent Predicate-Argument Structures: Unsupervised Constituency Parsing by Span Matching

arXiv:2404.12059v1 Announce Type: new
Abstract: Unsupervised constituency parsing is about identifying word sequences that form a syntactic unit (i.e., constituents) in a target sentence. Linguists identify the constituent by evaluating a set of Predicate-Argument Structure (PAS) equivalent sentences where we find the constituent corresponds to frequent word sequences. However, such information is unavailable to previous parsing methods which identify the constituent by observing sentences with diverse PAS. In this study, we empirically verify that \textbf{constituents correspond to word sequence patterns …

abstract arxiv cs.cl form identify parsing patterns set type unsupervised word