Skip to main content
Språkbanken Text is a department within Språkbanken.

BibTeX

@inProceedings{ahlberg-etal-2013-korp-178355,
	title        = {Korp and Karp – a bestiary of language resources: the research infrastructure of Språkbanken},
	abstract     = {A central activity in Språkbanken, an R&D unit at the University of Gothenburg, is the systematic construction of a research infrastructure based on interoperability and widely accepted standards for metadata and data. The two main components of this infrastructure deal with text corpora and with lexical resources. For modularity and flexibility, both components have a backend, or server-side part, accessed through an API made up of a set of well-defined web services. This means that there can be any number of different user interfaces to these components, corresponding, e.g., to different research needs. Here, we will demonstrate the standard corpus and lexicon search interfaces, designed primarily for linguistic searches: Korp and Karp.},
	booktitle    = {Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013), May 22–24, 2013, Oslo University, Norway. NEALT Proceedings Series 16},
	author       = {Ahlberg, Malin and Borin, Lars and Forsberg, Markus and Hammarstedt, Martin and Olsson, Leif-Jöran and Olsson, Olof and Roxendal, Johan and Uppström, Jonatan},
	year         = {2013},
	publisher    = {Linköping University Electronic Press},
	address      = {Linköping},
}

@techreport{hammarstedt-etal-2017-korp-256055,
	title        = {Korp 6 - Technical Report},
	author       = {Hammarstedt, Martin and Roxendal, Johan and Öhrman, Maria and Borin, Lars and Forsberg, Markus and Schumacher, Anne},
	year         = {2017},
	publisher    = {Institutionen för svenska språket, Göteborgs universitet},
}

@techreport{hammarstedt-etal-2017-korp-256056,
	title        = {Korp 6 - Användarmanual},
	author       = {Hammarstedt, Martin and Borin, Lars and Forsberg, Markus and Roxendal, Johan and Schumacher, Anne and Öhrman, Maria},
	year         = {2017},
	publisher    = {Institutionen för svenska språket, Göteborgs universitet},
}

@techreport{barnett-etal-2015-state-234687,
	title        = {State Chart XML (SCXML): State Machine Notation for Control Abstraction},
	abstract     = {This document describes SCXML, or the "State Chart extensible Markup Language". SCXML provides a generic state-machine based execution environment based on CCXML and Harel State Tables.},
	author       = {Barnett, Jim and Akolkar, Rahul and Auburn, RJ and Bodell, Michael and Burnett, Daniel C. and Carter, Jerry and McGlashan, Scott and Lager, Torbjörn and Helbing, Mark and Hosn, Rafah and Raman, T.V. and Reifenrath, Klaus and Rosenthal, No'am and Roxendal, Johan},
	year         = {2015},
	publisher    = {World Wide Web Consortium},
	address      = {Massachusetts, USA},
}

@techreport{roxendal-2013-state-189377,
	title        = {State Chart XML (SCXML): State Machine Notation for Control Abstraction – W3C Working Draft 6 December 2012},
	author       = {Roxendal, Johan},
	year         = {2013},
	publisher    = {MIT},
	address      = {Cambridge, USA},
}

@techreport{roxendal-2013-state-189376,
	title        = {State Chart XML (SCXML): State Machine Notation for Control Abstraction – W3C Last Call Working Draft 1 August 2013},
	author       = {Roxendal, Johan},
	year         = {2013},
	publisher    = {MIT},
	address      = {Cambridge, USA},
}

@inProceedings{borin-etal-2012-korp-156080,
	title        = {Korp – the corpus infrastructure of Språkbanken},
	abstract     = {We present Korp, the corpus infrastructure of Språkbanken (the Swedish Language Bank). The infrastructure consists of three main components: the Korp corpus pipeline, the Korp backend, and the Korp frontend. The Korp corpus pipeline is used for importing corpora, annotating them, and then exporting the annotated corpora into different formats. An essential feature of the pipeline is the ability to leave existing annotations untouched, both structural and word level annotations, and to use the existing annotations as the foundation of other annotations. The Korp backend consists of a set of REST-based web services for searching in and retrieving information about the corpora. Finally, the Korp frontend is a graphical search interface that interacts with the Korp backend. The interface has been inspired by corpus search interfaces such as SketchEngine, Glossa, and DeepDict, and it uses State Chart XML (SCXML) in order to enable users to bookmark interaction states. We give a functional and technical overview of the three components, followed by a discussion of planned future work.
},
	booktitle    = {Proceedings of LREC 2012. Istanbul: ELRA},
	author       = {Borin, Lars and Forsberg, Markus and Roxendal, Johan},
	year         = {2012},
	volume       = {Accepted},
	pages        = {474–478},
}

@inProceedings{junger-etal-2012-scxml-164522,
	title        = {SCXML for Building Conversational Agents in the Dialog Web Lab},
	abstract     = {The W3C has selected Harel Statecharts, under the name of State Chart XML (SCXML), as the basis for future stan- dards in the area of (multimodal) dialog systems (Barnett et al. 2012). In an effort to educate people about SCXML we are building a web-based development environment where the dialogs of embodied, spoken conversational agents can be managed and controlled using SCXML, in a playful and interesting manner.},
	booktitle    = {Proceedings of The Swedish Language Technology Conference (SLTC) 2012},
	author       = {Junger, David and Lager, Torbjörn and Roxendal, Johan},
	year         = {2012},
}

@inProceedings{muhlenbock-etal-2008-symbol-118066,
	title        = {Symbol supported news text on the internet - A corpus-based approach},
	booktitle    = {SLTC 2008: Proceedings of the Swedish Language Technology Conference},
	author       = {Mühlenbock, Katarina and Roxendal, Johan and Rudberg, Janaina and Lundälv, Mats},
	year         = {2008},
}