Automatic Labeling of Semantic Roles with a Dependency Parser in Hungarian Economic Texts

2015 ◽  
pp. 261-272
Author(s):  
Zoltán Subecz
Keyword(s):  
Semantic Roles ◽  
Economic Texts ◽  
Dependency Parser

Semantic structure and meaning within agentive nominal compounds: Evidence from French and Swedish

2010 ◽  
Vol 3 (2) ◽  
pp. 181-204 ◽  
Author(s):  
Maria Rosenberg
Keyword(s):  
Semantic Structure ◽  
Semantic Roles ◽  
Nominal Compounds

This study addresses agentive nominal compounds in French and Swedish containing N and V constituents. French has only one such compound, VN, whereas Swedish has at least four, NV-are, NV-a, NV and VN. The study explores the semantic characteristics of their constituents and their semantic structures. Formal aspects are also considered within a lexeme-based morphology. The analysis shows that, although French and Swedish compounds differ formally, they share more or less the same semantics. Their V constituent takes one or more arguments, and their N constituents display several semantic roles. Semantically, the compounds generally denote an Actor of verbs taking two arguments, and the N constituents denote an Undergoer, except in Swedish VN compounds, which denote an entity which fills the same role as that of the N constituent, generally an Actor. Non argumental interpretations, such as Place or Event, are less frequent. In conclusion, the study can have typological value for the semantics of agentive nominal compounds.1

scholarly journals The Proposition Bank: An Annotated Corpus of Semantic Roles

2005 ◽  
Vol 31 (1) ◽  
pp. 71-106 ◽  
Author(s):  
Martha Palmer ◽  
Daniel Gildea ◽  
Paul Kingsbury
Keyword(s):  
Automatic System ◽  
Semantic Representation ◽  
Higher Order ◽  
Practical Approach ◽  
Semantic Role ◽  
Syntactic Parsing ◽  
Semantic Roles ◽  
Syntactic Structures ◽  
Annotation Process ◽  
Types Of Information

The Proposition Bank project takes a practical approach to semantic representation, adding a layer of predicate-argument information, or semantic role labels, to the syntactic structures of the Penn Treebank. The resulting resource can be thought of as shallow, in that it does not represent coreference, quantification, and many other higher-order phenomena, but also broad, in that it covers every instance of every verb in the corpus and allows representative statistics to be calculated. We discuss the criteria used to define the sets of semantic roles used in the annotation process and to analyze the frequency of syntactic/semantic alternations in the corpus. We describe an automatic system for semantic role tagging trained on the corpus and discuss the effect on its performance of various types of information, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty “trace” categories of the treebank.

Ainu applicatives in typological perspective

2010 ◽  
Vol 34 (4) ◽  
pp. 749-801 ◽  
Author(s):  
Anna Bugaeva
Keyword(s):  
Exact Role ◽  
Semantic Roles

This paper explores the polyfunctionality, grammaticalization, and typological relevance of applicatives in Ainu. Applicatives are derived by the valency-increasing prefixes which are generally defined here as instrumental e-, dative ko-, and locative o-. The referential range of the respective constructions stretches over several semantic roles and the exact role is attributed to the interaction between the semantics of the prefix and verb. The typologically unusual properties of Ainu applicatives include the ability of e- applicatives to add the roles of Theme and Content, the ability of the so-called unaccusative intransitives to host applicative prefixes e- and ko-, the possibility of e-ko- and ko-e- double applicatives, the absence of non-applicative paraphrases for some applicatives, and the possibility of applicative object incorporation.

Interaction Transformation Patterns Based on Semantic Roles

2005 ◽  
pp. 239-250 ◽  
Author(s):  
Isabel Díaz ◽  
Lidia Moreno ◽  
Oscar Pastor ◽  
Alfredo Matteo
Keyword(s):  
Semantic Roles

scholarly journals Automatic Information Extraction from Text-Based Requirements

2021 ◽  
Vol 7 (1) ◽  
pp. 8-13
Author(s):  
Simon Fritz ◽  
◽  
Vethiga Srikanthan ◽  
Ryan Arbai ◽  
Chenwei Sun ◽  
...  
Keyword(s):  
Requirements Management ◽  
Small Companies ◽  
Semantic Roles ◽  
Semantic Data ◽  
Requirements Specifications ◽  
Automatic Information ◽  
Very High ◽  
Automatic Information Extraction ◽  
Integration Effort ◽  
Subsequent Integration

Requirements form the legal basis for many development pro-jects. They are usually exchanged between customer and supplier in the form of product and requirements specifications and re-quire a subsequent integration effort into the corresponding requirements management solutions. Especially for small and medium-sized enterprises (SME), which mainly use office solutions for the management of requirements, this involves a very high integration effort, which is why this is usually only partially managed or not managed at all. Software solutions available on the market already offer support, but they are too expensive or complex, especially for small companies. The project DAM4KMU, funded by German Federal Ministry for Education and Research (BMBF), addresses this challenge and by enabling SMEs from Germany to integrate requirement documents automatically into existing requirement structures with the help of NLP-based techniques. For this purpose, the documents to be processed are divided into semantic roles, which can then be transferred into a semantic data structure. This in turn enables an automatic linking of the requirements and system components, which reduces the manual effort and avoids possible errors.

Sign in / Sign up

Export Citation Format

Share Document