Automatic labeling of semantic roles

Abstract

We present a system for identifying the semantic relationships, or semantic roles, lled by constituents of a s e n tence within a semantic frame. Various lexical and syntactic features are derived from parse trees and used to derive statistical classi ers from hand-annotated training data.

A frame-based approach for capturing semantics from Arabic text for text-to-sign language MT

“…Many attempts based on FrameNet tenet have been experimented, from Multi-Lingual Lexicon Databases (MLLD) building (Boas 2005;Fung and Chen 2006;Pado and Lapata 2005;Fürstenau and Lapata 2009), information extraction (Moschitti et al 2003;Surdeanu et al 2003), text entailment (Burchardt and Frank 2006;Burchardt et al 2009;Tatu and Moldovan 2005), text categorization (Moschitti 2008), question answering (Narayanan and Harabagiu 2004; Shen and Lapata 2007;Frank et al 2007;Moschitti et al 2007), paraphrase recognition (Padó and Erk 2005), machine translation (Boas 2002;Wu and Fung 2009) and shallow semantic analysis and role labeling (Gildea and Jurafsky 2002;Thompson et al 2003;Fleischman et al 2003;Shi and Mihalcea 2005;Erk and Padó 2006;Giuglea and Moschitti 2006;Johansson and Nugues 2007;Matsubayashi et al 2009;Fürstenau and Lapata 2009;Deschacht and Moens 2009;Lang and Lapata 2011;Titov and Klementiev 2012). 6 Frame based approach to Arabic text semantics In our project, we describe techniques for automatic semantic analysis of Arabic texts with deeper grain level than SRL analysis using a dependency-based deep analysis and following a frame semantics approach. We use a dependency syntax parser which integrates the BAMA analyzer with a lexical semantics analyzer based on AWN database in a single model.…”

“…Due to robustness, low level of ambiguities involved, and processing speed, shallow semantic parsing remain most popular than deep analysis in NLP community. Since shallow semantic parsers are mainly concerned with assigning semantic roles to syntactic arguments of a predicate (Gildea and Jurafsky 2002), they only provide limited and local representations , and dismiss a lot of information (Ruppenhofer et al 2010a, b) such as relations between different local semantic argument structures. However, many applications like Machine Translation and Language Generation need for deeper semantic parsing that extract the overall meaning of natural language texts by capturing features of meaning anchored in features of linguistic form in fine grained linguistic analyses.…”

“…Thus, we use two types of frames (1) A mapping frame, which ''records exactly how the language relates frame elements to those syntactic constituents that are syntactically dependent on the lexical items that evoke the frame'' . In addition to the standard triple information, the grammatical function and the functional syntactic type of the phrase expressing the semantic role (Gildea and Jurafsky 2002), the mapping frame describes all possible combinations of frame elements and their syntactic realizations such as alternation between transitive and intransitive uses of the verb, variation in arguments position within the sentence and their possible morpho-syntactic realizations. (2) A semantic frame, which describes the underlying deep semantic structure of the prototypical situation depicted by the predicate and its arguments as a semantic dependency graph.…”

“…Shallow parsing (Gildea and Jurafsky 2002) is used to make link between underlying meaning and surface realization of the argument structure in order to map sentence chunks to semantic roles. However, this useful kind of analysis is insufficient for some NLP tasks such as MT.…”

Integration of Multiple Classifiers for Chinese Semantic Dependency Analysis

“…Semantic parsing using statistical and machine learning methods [5] has been heavily studied. Annotated corpora such as FrameNet [8] and the proposition Bank [13] have been created.…”