Paper Info
Title
From Discourse Representation Structure to event semantics: A simple conversion?
Abstract
Many applications in Natural Language Processing require a semantic analysis of sentences in terms of truth-conditional representations, often with specific desiderata in terms of which information needs to be included in the semantic analysis. However, there are only very few tools that allow such an analysis. We investigate the representations of an automatic analysis pipeline of the C&C parser and Boxer to determine whether Boxer's analyses in form of Discourse Representation Structure can be successfully converted into a more surface oriented event semantic representation, which will serve as input for a fusion algorithm for fusing hard and soft information. We use a data set of synthetic counter intelligence messages for our investigation. We provide a basic pipeline for conversion and subsequently discuss areas in which ambiguities and differences between the semantic representations present challenges in the conversion process.
Year
DOI
Venue
2016
10.15439/2016F440
2016 Federated Conference on Computer Science and Information Systems (FedCSIS)
Keywords
Field
DocType
discourse representation structure,event semantics,natural language processing,semantic analysis,truth-conditional representations,desiderata,automatic analysis pipeline,surface oriented event semantic representation,fusion algorithm,synthetic counter intelligence messages,conversion process
Pipeline transport,Information needs,Computer science,Grammar,Natural language processing,Artificial intelligence,Parsing,MultiNet,Semantic computing,Machine learning,Semantics,Semantic compression
Conference
Volume
ISSN
ISBN
8
2300-5963
978-1-5090-0046-3
Citations 
PageRank 
References 
1
0.37
16
Authors
2
Name
Order
Citations
PageRank
Daniel Dakota121.75
Sandra Kübler25613.29