Semantic Parsing via $l_{0}$-norm-based Alignment

In this paper, we explore the IBM Model with a `0-norm prior to the semantic parsing which parses a sentence to its corresponding meaning representation, and compare two supervised probabilistic Combinatory Categorial Grammar (PCCG) online learning approaches that are Unification-Based Learning (UBL) method and Factored Unification-Based Learning (FUBL) one. Specially, we extend manually GeoQuery and ATIS datasets from English to Chinese pinyinformat string. The experiment on such benchmark datasets in both English and Chinese with two different meaning representations (i.e., lambda-calculus and variable-free expressions) demonstrates that both methods adopted this IBM Model with `0-norm outperform trivially those that used the IBM Model without `0norm, and also shows small improvements of around 0.1% ∼ 0.7% of F1 for the two algorithms on nearly all conditions.