BibTeX

@misc{andersen-forsberg-2012-sibirientyska-162958,
	title        = {Sibirientyska},
	abstract     = {German in Siberia are transcriptions of German spoken in the region of Krasnoyarsk (Russia). The corpus contains about 34 000 running words. Codeswitching to Russian and verb forms are annotated (Russian word forms in brackets like [vot], finite verb forms (FINIT), infinite verb forms (INFIN)). The transcription and annotation of the corpus have been established in collaboration with the Astafyev University Krasnoyarsk. The corpus is a part of a research project at the University of Gothenburg, see http://www.sprak.gu.se/kontakta-oss/larare/andersen-christiane/syntax-in-contact/
The data base is currently in the test phase.

},
	author       = {Andersen, Christiane and Forsberg, Markus},
	year         = {2012},
	publisher    = {University of Gothenburg},
	address      = {Göteborg},
}

@inProceedings{borin-etal-2012-search-157338,
	title        = {Search Result Diversification Methods to Assist Lexicographers},
	abstract     = {We show how the lexicographic task of finding informative and diverse example sentences can be cast as a search result diversification problem, where an objective based on relevance and diversity is maximized. This problem has been studied intensively in the information retrieval community during recent years, and efficient algorithms have been devised.

We finally show how the approach has been implemented in a
lexicographic project, and describe the relevance and diversity
functions used in that context.
},
	booktitle    = {Proceedings of the 6th Linguistic Annotation Workshop},
	author       = {Borin, Lars and Forsberg, Markus and Friberg Heppin, Karin and Johansson, Richard and Kjellandsson, Annika},
	year         = {2012},
	pages        = {113--117},
}

@inProceedings{borin-etal-2012-transferring-157213,
	title        = {Transferring Frames: Utilization of Linked Lexical Resources},
	abstract     = {In our experiment, we evaluate the transferability of  frames from Swedish to Finnish in parallel corpora. We evaluate both the theoretical possibility of transferring frames and the possibility of performing it using available lexical resources. We add the frame information to an extract of the Swedish side of the Kotus and JRC-Acquis corpora using an automatic frame labeler and copy it to the Finnish side. We focus on evaluating the results to get an estimation on how often the parallel sentences can be said to
express the same frame. This sheds light to the questions: Are the same situations in the two languages expressed using different frames, i.e. are the frames transferable even in theory? How well can the frame information of running text be transferred from language to another?
},
	booktitle    = {Proceedings of the Workshop on Inducing Linguistic Structure Submission (WILS)},
	author       = {Borin, Lars and Forsberg, Markus and Johansson, Richard and Muhonen, Kristiina and Purtonen, Tanja and Voionmaa, Kaarlo},
	year         = {2012},
	pages        = {8--15},
}

@inProceedings{borin-etal-2012-growing-171988,
	title        = {Growing a Swedish constructicon in lexical soil},
	booktitle    = {Proceedings of the Swedish Language Technology Conference. Lund, October 24-26, 2012},
	author       = {Borin, Lars and Forsberg, Markus and Lyngfelt, Benjamin and Prentice, Julia and Rydstedt, Rudolf and Sköldberg, Emma and Tingsell, Sofia},
	year         = {2012},
	pages        = {10--11},
}

@inProceedings{borin-etal-2012-open-156079,
	title        = {The open lexical infrastructure of Språkbanken},
	abstract     = {We present our ongoing work on Karp, Språkbanken’s (the Swedish Language Bank) open lexical infrastructure, which has two main functions: (1) to support the work on creating, curating, and integrating our various lexical resources; and (2) to publish daily versions of the resources, making them searchable and downloadable. An important requirement on the lexical infrastructure is also that we maintain a strong bidirectional connection to our corpus infrastructure. At the heart of the infrastructure is the SweFN++ project with the goal to create free Swedish lexical resources geared towards language technology applications. The infrastructure currently hosts 15 Swedish lexical resources, including historical ones, some of which have been created from scratch using existing free resources, both external and in-house. The resources are integrated through links to a pivot lexical resource, SALDO, a large morphological and lexical-semantic resource for modern Swedish. SALDO has been selected as the pivot partly because of its size and quality, but also because its form and sense units have been assigned persistent identifiers (PIDs) to which the lexical information in other lexical resources and in corpora are linked.},
	booktitle    = {Proceedings of the 8th International Conference on Language Resources and Evaluation : May 23-25, 2012 / eds. Nicoletta Calzolari },
	author       = {Borin, Lars and Forsberg, Markus and Olsson, Leif-Jöran and Uppström, Jonatan},
	year         = {2012},
	ISBN         = {978-2-9517408-7-7},
	pages        = {3598--3602},
}

@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{forsberg-lager-2012-cloud-156078,
	title        = {Cloud Logic Programming for Integrating Language Technology Resources},
	abstract     = {The main goal of the CLT Cloud project is to equip lexica, morphological processors, parsers and other software components developed within CLT (Centre of Language Technology) with so called web API:s, thus making them available on the Internet in the form of web services. We present a proof-of-concept implementation of the CLT Cloud server where we use the logic programming language Prolog for composing and aggregating existing web services into new web services in a way that encourages creative exploration and rapid prototyping of LT applications.
},
	booktitle    = {Proceedings of LREC 2012},
	author       = {Forsberg, Markus and Lager, Torbjörn},
	year         = {2012},
	volume       = {Accepted},
}

@inProceedings{kokkinakis-etal-2012-literacy-164587,
	title        = {Literacy Demands and Information to Cancer Patients},
	abstract     = {This study examines language complexity of written health information materials for patients undergoing colorectal cancer surgery. Written and printed patient information from 28 Swedish clinics are automatically analyzed by means of language technology. The analysis reveals different problematic issues that might have impact on readability. The study is a first step, and part of a larger project about patients’ health information seeking behavior in relation to written information material. Our study aims to provide support for producing more individualized, person centered information materials according to preferences for complex and detailed or legible texts and thus enhance a movement from receiving information and instructions to participating in knowing. In the near future the study will continue by integrating focus groups with patients that may provide valuable feedback and enhance our knowledge about patients’ use and preferences of different information material.},
	booktitle    = {Proceedings of the 15th International Conference on Text, Speech and Dialogue},
	author       = {Kokkinakis, Dimitrios and Forsberg, Markus and Johansson Kokkinakis, Sofie and Smith, Frida and Öhlén, Joakim},
	year         = {2012},
	ISBN         = {978-364232789-6},
}

@inProceedings{lyngfelt-etal-2012-adding-163582,
	title        = {Adding a constructicon to the Swedish resource network of Språkbanken},
	abstract     = {This paper presents the integrated Swedish resource network of Språkbanken in general, and its latest addition – a constructicon – in particular. The constructicon, which is still in its early stages, is a collection of (partially) schematic multi-word units, constructions, developed as an addition to the Swedish FrameNet (SweFN). SweFN and the constructicon are integrated with other parts of Språkbanken, both lexical resources and corpora, through the lexical resource SALDO. In most respects, the constructicon is modeled on its English counterpart in Berkeley, and, thus, following the FrameNet format. The most striking differencies are the inclusion of so-called collostructional elements and the treatment of semantic roles, which are defined globally instead of locally as in FrameNet. Incorporating subprojects such as developing methods for automatic identification of constructions in authentic text on the one hand, and accounting for constructions problematic for L2 acquisition on the other, the approach is highly cross-disciplinary in nature, combining various theoretical linguistic perspectives on construction grammar with language technology, lexicography, and L2 research.},
	booktitle    = {11th Conference on Natural Language Processing (KONVENS) Proceedings},
	author       = {Lyngfelt, Benjamin and Borin, Lars and Forsberg, Markus and Prentice, Julia and Rydstedt, Rudolf and Sköldberg, Emma and Tingsell, Sofia},
	year         = {2012},
	ISBN         = {3-85027-005-X},
	pages        = {452--461},
}

@techreport{lyngfelt-forsberg-2012-svenskt-158226,
	title        = {Ett svenskt konstruktikon. Utgångspunkter och preliminära ramar},
	author       = {Lyngfelt, Benjamin and Forsberg, Markus},
	year         = {2012},
	publisher    = {University of Gothenburg},
	address      = {Göteborg},
}

@inProceedings{pedersen-etal-2012-linking-155599,
	title        = {Linking and validating Nordic and Baltic wordnets},
	booktitle    = {Proceedings of the 6th International Global Wordnet Conference},
	author       = {Pedersen, Bolette Sandford and Borin, Lars and Forsberg, Markus and Lindén, Krister and Orav, Heili and Rögnvaldsson, Eírikur},
	year         = {2012},
	volume       = {Accepted},
	pages        = {254--260},
}

@misc{ranta-forsberg-2012-implementing-168685,
	title        = {Implementing Programming Languages},
	author       = {Ranta, Aarne and Forsberg, Markus},
	year         = {2012},
	publisher    = {College Publications},
	address      = {London},
	ISBN         = {978-1-84890-064-6},
}

@inProceedings{smith-etal-2012-forbattra-170895,
	title        = {Hur kan vi förbättra skriftligt informations- och utbildningsmaterial för patienter som opereras elektivt för kolorektal cancer?},
	abstract     = {Kolorektal cancer (KRC) är den tredje största cancerdiagnosen i Sverige med drygt 5500 drabbade årligen. Primär behandling är kirurgi kompletterad av pre- och postoperativ onkologisk behandling. Standardiserade koncept för accelererat vårdförlopp med kortare vårdtider lägger mycket fokus på fysisk rehabilitering, men mindre på den psykiska påfrestning det innebär att bli opererad för en cancerdiagnos. Patienter förväntas ta stort ansvar för sin rehabilitering, både på sjukhuset och hemma. För att vara förberedd behövs både skriftlig och muntlig information.
Syftet med studien var att kartlägga och karaktärisera det skriftliga informations- och utbildningsmaterial (IOU) som används till patienter som opereras elektivt för KRC. Vidare var syftet att beskriva patienters uppfattning om struktur och innehåll på IOU.
IOU från 28 kliniker som opererar patienter med KRC samlades in (totalt 220 st). För att kunna ge ett mått på texternas svårighetsgrad gjordes språkteknologisk analys på samtliga IOU, där bl.a. ordlängd, meningsbyggnad och jämförelse med annan typ av litteratur mättes På 117 st gjordes en suitabilityanalys med instrumentet SAM+CAM där domän som innehåll, läsbarhet, bilder, layout samt stimulans och motivation för lärande bedömdes. Fem fokusgrupper med patienter genomfördes där patienterna uppmanades att berätta om vad de tycker utmärker ett bra respektive dåligt IOU, vad de saknar i innehåll och när och på vilket sätt de vill ha materialet utlämnat.
Resultatet av språkteknologiska- och suitabilityanalysen visar att de flesta IOU bedömdes som ”adequate”, men spridningen var stor. Patienterna hade önskemål om mer nivåuppdelat/nivåriktat material, där man själv kan välja hur mycket information man vill ha vid ett visst tillfälle. Flera ämnen saknades, eller var för otydligt beskrivna för att patienterna skulle känna sig trygga vid hemgång. 
Resultatet av de tre analysmetoderna bör kunna användas för att utveckla en ”verktygslåda” för att i framtiden kunna utforma bättre riktat IOU för patientgruppen.
},
	booktitle    = {Nationella konferensen i Cancervård, 24-25 maj 2012, Stockholm},
	author       = {Smith, Frida and Öhlén, Joakim and Carlsson, Eva and Forsberg, Markus and Kokkinakis, Dimitrios and Friberg, Febe},
	year         = {2012},
}

@article{smith-etal-2012-studie-170897,
	title        = {Ny studie visar hur information till patienter med kolorektal cancer kan förbättras},
	abstract     = {Skriftligt informationsmaterial är ofta skrivet på för hög nivå och ställer höga krav på den tänkta läsaren (patienten).  Förutom läsbarhet finns det fler faktorer att utvärdera för att se om materialet är lämpligt. Innehåll, struktur, layout och typsnitt, illustrationer och lärande och motivation är sådant som bör tas hänsyn till. Ett lämpligare, bättre anpassat material kan hjälpa personer med sjukdom att ställa bättre frågor när de har samtal med vårdpersonal och det kan göra personen mindre osäker och orolig för det okända som väntar. En ny studie som ingår i forskningsprojektet PINCORE (personcentred information and communication in colorectal cancer care) syftar till att förbättra information och kommunikation vid kolorektal cancer.},
	journal      = {Cancervården},
	author       = {Smith, Frida and Öhlén, Joakim and Carlsson, Eva and Friberg, Febe and Forsberg, Markus and Kokkinakis, Dimitrios},
	year         = {2012},
	number       = {5},
	pages        = {18--21},
}

@inProceedings{vasiljevs-etal-2012-creation-156083,
	title        = {Creation of an Open Shared Language Resource Repository in the Nordic and Baltic Countries},
	abstract     = {The META-NORD project has contributed to an open infrastructure for language resources (data and tools) under the META-NET umbrella. This paper presents the key objectives of META-NORD and reports on the results achieved in the first year of the project. META-NORD has mapped and described the national language technology landscape in the Nordic and Baltic countries in terms of language use, language technology and resources, main actors in the academy, industry, government and society; identified and collected the first batch of language resources in the Nordic and Baltic countries; documented, processed, linked, and upgraded the identified language resources to agreed standards and guidelines. The three horizontal multilingual actions in META-NORD are overviewed in this paper: linking and validating Nordic and Baltic wordnets, the harmonisation of multilingual Nordic and Baltic treebanks, and consolidating multilingual terminology resources across European countries. This paper also touches upon intellectual property rights for the sharing of language resources.
},
	booktitle    = {Proceedings of LREC 2012},
	author       = {Vasiļjevs, Andrejs and Forsberg, Markus and Gornostay, Tatiana and Hansen, Dorte H. and Jóhannsdóttir, Kristín M. and Lindén, Krister and Lyse, Gunn I. and Offersgaard, Lene and Oksanen, Ville and Olsen, Sussi and Pedersen, Bolette S. and Rögnvaldsson, Eiríkur and Rozis, Roberts and Skadiņa, Inguna and Smedt, Koenraad De},
	year         = {2012},
	ISBN         = {978-2-9517408-7-7},
}