On WordNet Semantic Classes and Dependency Parsing

Abstract

This paper presents experiments with WordNet semantic classes to improve dependency parsing. We study the effect of semantic classes in three dependency parsers, using two types of constituencyto-dependency conversions of the English Penn Treebank. Overall, we can say that the improvements are small and not significant using automatic POS tags, contrary to previously published results using gold POS tags (Agirre et al., 2011). In addition, we explore parser combinations, showing that the semantically enhanced parsers yield a small significant gain only on the more semantically oriented LTH treebank conversion.

Creating Effective Marketing Messages Through Moderately Surprising Syntax

“…When parsing, people automatically assess the syntactic relationships between the words and extract the meaning of the sentence. The syntactic relationships between the words are referred to as dependencies (McDonald et al 2013; Nivre 2005). For example, to comprehend the sentence “Amazon delivers diapers,” a person has to identify the dependencies among the three syntactic elements—the noun “Amazon” (the subject), the verb “delivers” (the action), and the noun “diapers” (the object).…”

WHUNlp at SemEval-2016 Task DiMSUM: A Pilot Study in Detecting Minimal Semantic Units and their Meanings using Supervised Models

“…In the community of natural language processing, multiword expressions (MWEs) detection (Schneider et al, 2014b;Schneider et al, 2014a) and supersense tagging (Ciaramita and Johnson, 2003;Ciaramita and Altun, 2006) have received much research attention due to their various applications such as syntactic parsing (Candito and Constant, 2014;Bengoetxea et al, 2014), semantic parsing (Banarescu et al, 2013), and machine translation (Carpuat and Diab, 2010). However, not much attention has been paid to the relationship between MWEs and supersenses (Piao et al, 2005;Schneider and Smith, 2015 The DiMSUM shared task (Schneider et al, 2016) at SemEval 2016 aims to predict a broad-coverage representation of lexical semantics giving an English sentence.…”