Semantic Kernels for Semantic Parsing
Iman Saleh, Alessandro Moschitti, Preslav Nakov, Lluı́s Màrquez, Shafiq Joty · 2014
We present an empirical study on the use of semantic information for Concept Seg-mentation and Labeling (CSL), which is an important step for semantic parsing. We represent the alternative analyses out-put by a state-of-the-art CSL parser with tree structures, which we rerank with a classifier trained on two types of seman-tic tree kernels: one processing structures built with words, concepts and Brown clusters, and another one using semantic similarity among the words composing the structure. The results on a corpus from the restaurant domain show that our semantic kernels exploiting similarity measures out-perform state-of-the-art rerankers. 1