Formal Mechanisms for Capturing Regularizations

Abstract

While initial treebanks and treebank parsers primarily involved surface analysis, recent work focuses on predicate argument (PA) structure. PA structure provides means to regularize variants (e.g., actives/passives) of sentences so that individual patterns may have better coverage (in MT, QA, IE, etc.), offsetting the sparse data problem. We encode such PA information in the GLARF framework. Our previous work discusses procedures for producing GLARF from treebanks and parsed data. This paper shows  that GLARF is particularly well-suited for capturing regularization. We discuss crucial components of GLARF and demonstrate that other frameworks would require equivalent components to adequately express regularization.

Resources

Details