Improving Chinese-English PropBank Alignment

Abstract

We describe 2 improvements to Chinese-English PropBank predicate-argument structure alignment. Taking advantage of the recently expanded PropBank English nominal and adjective predicate annotation (Bonial et al., 2014), we performed predicateargument alignments between both verb and nominal/adjective predicates in Chinese and English. Using our alignment system, this increased the number of aligned predicateargument structures by 24.5% on the parallel Xinhua News corpus. We also improved the PropBank alignment system using expectation-maximization (EM) techniques. By collecting Chinese-English predicate-topredicate and argument type-to-argument type alignment probabilities and iteratively improving the alignment output using these probabilities on a large unannotated parallel corpora, we improved the predicate alignment performance by 1 F point when using all automatic SRL and word alignment inputs.

Connecting Symbolic Statutory Reasoning with Legal Information Extraction

“…Closer to this work, the PropBank dataset (Palmer et al, 2005;O'Gorman et al, 2018) adds predicate-argument relations on top of the Penn Treebank parse trees (Marcus et al, 1993). This effort has been extended to more languages (Moeller et al, 2020;Anwar et al, 2016;Wu and Palmer, 2015). The structures considered here are represented using Neo-Davidsonian semantics (Castañeda, 1967;Davidson, 1967;Parsons, 1990).…”