BibTeX

@inProceedings{rouces-etal-2018-generating-264719,
	title        = {Generating a Gold Standard for a Swedish Sentiment Lexicon},
	abstract     = {We create a gold standard for sentiment annotation of Swedish terms, using the freely available SALDO lexicon and the Gigaword
corpus. For this purpose, we employ a multi-stage approach combining corpus-based frequency sampling, direct score annotation and
Best-Worst Scaling. In addition to obtaining a gold standard, we analyze the data from our process and we draw conclusions about the
optimal sentiment model.},
	booktitle    = {LREC 2018, Eleventh International Conference on Language Resources and Evaluation, May 7-12, 2018, Miyazaki (Japan)},
	author       = {Rouces, Jacobo and Tahmasebi, Nina and Borin, Lars and Rødven-Eide, Stian },
	year         = {2018},
	publisher    = {ELRA},
	address      = {Miyazaki},
	ISBN         = {979-10-95546-00-9},
}

@inProceedings{rouces-etal-2018-sensaldo-264720,
	title        = {SenSALDO: Creating a Sentiment Lexicon for Swedish},
	abstract     = {The natural language processing subfield known as sentiment analysis or opinion mining has seen an explosive expansion over the
last decade or so, and sentiment analysis has become a standard item in the NLP toolbox. Still, many theoretical and methodological
questions remain unanswered and resource gaps unfilled. Most work on automated sentiment analysis has been done on English and
a few other languages; for most written languages of the world, this tool is not available. This paper describes the development of an
extensive sentiment lexicon for written (standard) Swedish. We investigate different methods for developing a sentiment lexicon for
Swedish. We use an existing gold standard dataset for training and testing. For each word sense from the SALDO Swedish lexicon,
we assign a real value sentiment score in the range [-1,1] and produce a sentiment label. We implement and evaluate three methods:
a graph-based method that iterates over the SALDO structure, a method based on random paths over the SALDO structure and a
corpus-driven method based on word embeddings. The resulting sense-disambiguated sentiment lexicon (SenSALDO) is an open source
resource and freely available from Språkbanken, The Swedish Language Bank at the University of Gothenburg.},
	booktitle    = {LREC 2018, Eleventh International Conference on Language Resources and Evaluation, 7-12 May 2018, Miyazaki (Japan)},
	author       = {Rouces, Jacobo and Tahmasebi, Nina and Borin, Lars and Rødven-Eide, Stian },
	year         = {2018},
	publisher    = {ELRA},
	address      = {Miyazaki},
	ISBN         = {979-10-95546-00-9},
}

@inProceedings{rouces-etal-2018-defining-264721,
	title        = {Defining a gold standard for a Swedish sentiment lexicon: Towards higher-yield text mining in the digital humanities},
	abstract     = {There is an increasing demand for multilingual sentiment analysis, and most work on
sentiment lexicons is still carried out based on English lexicons like WordNet. In addition, many
of the non-English sentiment lexicons that do exist have been compiled by (machine) translation
from English resources, thereby arguably obscuring possible language-specific characteristics
of sentiment-loaded vocabulary. In this paper we describe the creation from scratch of a gold
standard for the sentiment annotation of Swedish terms as a first step towards the creation of a
full-fledged sentiment lexicon for Swedish.},
	booktitle    = {CEUR Workshop Proceedings vol. 2084.  Proceedings of the Digital Humanities in the Nordic Countries 3rd Conference Helsinki, Finland, March 7-9, 2018.  Edited by  Eetu Mäkelä Mikko Tolonen Jouni Tuominen },
	author       = {Rouces, Jacobo and Borin, Lars and Tahmasebi, Nina and Rødven-Eide, Stian },
	year         = {2018},
	publisher    = {University of Helsinki, Faculty of Arts},
	address      = {Helsinki},
}

@inProceedings{borin-etal-2018-language-290841,
	title        = {Language technology for digital linguistics: Turning the Linguistic Survey of India into a rich source of linguistic information},
	abstract     = {We present our work aiming at turning the linguistic material available in Grierson’s classical Linguistic Survey of India (LSI) from a printed discursive textual description into a formally structured digital language resource, a database suitable for a broad array of linguistic investigations of the languages of South Asia. While doing so, we develop state-of-the-art language technology for automatically extracting the relevant grammatical information from the text of the LSI, and interactive linguistic information visualization tools for better analysis and comparisons of languages based on their structural and functional features.},
	booktitle    = {Lecture Notes in Computer Science. Computational Linguistics and Intelligent Text Processing, 18th International Conference, CICLing 2017, Budapest, Hungary, April 17–23, 2017},
	author       = {Borin, Lars and Virk, Shafqat and Saxena, Anju},
	year         = {2018},
	publisher    = {Springer},
	address      = {Cham},
}

@misc{pilan-etal-2018-proceedings-275358,
	title        = {Proceedings of the 7th Workshop on NLP for Computer Assisted Language Learning (NLP4CALL 2018), SLTC, Stockholm, 7th November 2018 },
	abstract     = {The primary goal of the workshop series on Natural Language Processing for Computer-Assisted Language Learning (NLP4CALL) is to create a meeting place for researchers working on the integration of Natural Language Processing and Speech Technologies in CALL systems and exploring the theoretical and methodological issues arising in this connection. The latter includes, among others, insights from Second Language Acquisition (SLA) research, on the one hand, and promoting the development of “Computational SLA” through setting up Second Language research infrastructure(s), on the other.

The intersection of Natural Language Processing (or Language Technology / Computational Linguistics) and Speech Technology with Computer-Assisted Language Learning (CALL) brings “understanding” of language to CALL tools, thus making CALL intelligent. This fact has given the name for this area of research – Intelligent CALL, ICALL. As the definition suggests, apart from having excellent knowledge of Natural Language Processing and/or Speech Technology, ICALL researchers need good insights into second language acquisition theories and practices, as well as knowledge of second language pedagogy and didactics. This workshop invites therefore a wide range of ICALL-relevant research, including studies where NLP-enriched tools are used for testing SLA and pedagogical theories, and vice versa, where SLA theories, pedagogical practices or empirical data are modeled in ICALL tools. The NLP4CALL workshop series is aimed at bringing together competencies from these areas for sharing experiences and brainstorming around the future of the field.},
	author       = {Pilán, Ildikó and Volodina, Elena and Alfter, David and Borin, Lars},
	year         = {2018},
	publisher    = {Linköping University Electronic Press},
	address      = {Linköpings universitet},
	ISBN         = {978-91-7685-173-9},
}

@inProceedings{alfter-etal-2018-from-275364,
	title        = {From Language Learning Platform to Infrastructure for Research on Language Learning},
	abstract     = {Lärka is an Intelligent Computer-Assisted Language Learning (ICALL) platform developed at Språkbanken, as a flexible and a valuable source of additional learning material (e.g. via corpus- based exercises) and a support tool for both teachers and L2 learners of Swedish and students of (Swedish) linguistics. Nowadays, Lärka is being adapted into a central building block in an emerging second language research infrastructure within a larger context of the text-based research infrastructure developed by the national Swedish Language bank, Språkbanken, and SWE-CLARIN.},
	booktitle    = {Proceedings of CLARIN-2018 conference, Pisa, Italy},
	author       = {Alfter, David and Borin, Lars and Pilán, Ildikó and Lindström Tiedemann,  Therese  and Volodina, Elena},
	year         = {2018},
}

@inProceedings{adesam-etal-2018-eukalyptus-273839,
	title        = {The Eukalyptus Treebank of Written Swedish},
	booktitle    = {Seventh Swedish Language Technology Conference (SLTC), Stockholm, 7–9 November 2018},
	author       = {Adesam, Yvonne and Bouma, Gerlof and Johansson, Richard and Borin, Lars and Forsberg, Markus},
	year         = {2018},
}

@incollection{haugen-borin-2018-danish-267403,
	title        = {Danish, Norwegian and Swedish},
	booktitle    = {The world's major languages},
	editor       = {Bernard Comrie},
	author       = {Haugen, Einar and Borin, Lars},
	year         = {2018},
	publisher    = {Routledge},
	address      = {London and New York},
	ISBN         = {9781138184824},
	pages        = {127--150},
}

@incollection{borin-etal-2018-linguistics-269084,
	title        = {Linguistics vs. language technology in constructicon building and use},
	abstract     = {In this chapter, we describe the close interaction of linguists and language technologists in the Swedish constructicon project. This kind of collaboration is not so common today, because of the way that language technology has developed in recent decades, but in our case the collaboration has been very successful, and constituted a genuine instance of cross-fertilization, where an evolving language technology infrastructure and a computational lexical macroresource described in the chapter has formed an integral part of the Swedish constructicon development environment, while at the same time the structured linguistic knowledge described in the constructicon has informed the language technology making up the infrastructure.},
	booktitle    = {Constructicography: Constructicon development across languages},
	editor       = {Benjamin Lyngfelt and Lars Borin and Kyoko Ohara and Tiago Timponi Torrent},
	author       = {Borin, Lars and Dannélls, Dana and Gruzitis, Normunds},
	year         = {2018},
	publisher    = {John Benjamins},
	address      = {Amsterdam},
	ISBN         = {9789027263865},
	pages        = {229--253},
}

@edited_book{lyngfelt-etal-2018-constructicography-269082,
	title        = {Constructicography: Constructicon development across languages},
	abstract     = {In constructionist theory, a constructicon is an inventory of constructions making up the full set of linguistic units in a language. In applied practice, it is a set of construction descriptions – a “dictionary of constructions”. The development of constructicons in the latter sense typically means combining principles of both construction grammar and lexicography, and is probably best characterized as a blend between the two traditions. We call this blend constructicography.

The present volume is a comprehensive introduction to the emerging field of constructicography. After a general introduction follow six chapters presenting constructicon projects for English, German, Japanese, Brazilian Portuguese, Russian, and Swedish, respectively, often in relation to a framenet of the language. In addition, there is a chapter addressing the interplay between linguistics and language technology in constructicon development, and a final chapter exploring the prospects for interlingual constructicography.

This is the first major publication devoted to constructicon development and it should be particularly relevant for those interested in construction grammar, frame semantics, lexicography, the relation between grammar and lexicon, or linguistically informed language technology.
},
	editor       = {Lyngfelt, Benjamin and Borin, Lars and Ohara, Kyoko and Torrent, Tiago Timponi},
	year         = {2018},
	publisher    = {John Benjamins},
	address      = {Amsterdam},
	ISBN         = {9789027263865},
}

@incollection{lyngfelt-etal-2018-constructicography-269085,
	title        = {Constructicography at work: Theory meets practice in the Swedish constructicon},
	abstract     = {This chapter addresses central topics in constructicography from the viewpoint of the Swedish constructicon project (SweCcn), focusing on practical constructicon development. The full process of construction description is described and discussed, from selection via corpus analysis to finished constructicon entry and beyond, towards structuring the set of entries into a network. Particular
attention is given to the description format and the treatment of constructional variation. A main theme in the chapter is the interdependence and alignment of SweCcn and related resources, on the one hand in the local context, notably the infrastructure of Språkbanken (the Swedish language bank), and on the other hand with respect to corresponding resources for other languages. Of key concern is the relation to FrameNet, both the Swedish and other framenets, and a major section is devoted to conditions for linking constructions and frames.},
	booktitle    = {Constructicography: Constructicon development across languages},
	editor       = {Benjamin Lyngfelt and Lars Borin and Kyoko Ohara and Tiago Timponi Torrent},
	author       = {Lyngfelt, Benjamin and Bäckström, Linnéa and Borin, Lars and Ehrlemark, Anna and Rydstedt, Rudolf},
	year         = {2018},
	publisher    = {John Benjamins},
	address      = {Amsterdam},
	ISBN         = {9789027263865},
	pages        = {41--106},
}

@incollection{borin-edlund-2018-language-269047,
	title        = {Language technology and 3rd wave HCI: Towards phatic communication and situated interaction},
	abstract     = {In the field of language technology, researchers are starting to pay more attention to various interactional aspects of language – a development prompted by a confluence of factors, and one which applies equally to the processing of written and spoken language. Notably, the so-called ‘phatic’ aspects of linguistic communication are coming into focus in this work, where linguistic interaction is increasingly recognized as being fundamentally situated. This development resonates well with the concerns of third wave HCI, which involves a shift in focus from stating the requirements on HCI design primarily in terms of “context-free” information flow, to a view where it is recognized that HCI – just like interaction among humans – is indissolubly embedded in complex, shifting contexts. These – together with the different backgrounds and intentions of interaction participants – shape the interaction in ways which are not readily understandable in terms of rational information exchange, but which are nevertheless central aspects of the interaction, and which therefore must be taken into account in HCI design, including its linguistic aspects, forming the focus of this chapter.},
	booktitle    = {New Directions in Third Wave Human-Computer Interaction: Volume 1 - Technologies},
	editor       = {Michael Filimowicz and Veronika Tzankova.},
	author       = {Borin, Lars and Edlund, Jens},
	year         = {2018},
	publisher    = {Springer International Publishing},
	address      = {Cham},
	ISBN         = {978-3-319-73355-5},
	pages        = {251--264},
}

@inProceedings{malm-etal-2018-lingfn-267404,
	title        = {LingFN: Towards a framenet for the linguistics domain},
	abstract     = {Framenets and frame semantics have proved useful for a number of natural language processing (NLP) tasks. However, in this connection framenets have often been criticized for limited coverage. A proposed reasonable-effort solution to this problem is to develop domain-specific (sublanguage) framenets to complement the corresponding general-language framenets for particular NLP tasks, and in the literature we find such initiatives covering, e.g., medicine, soccer, and tourism. In this paper, we report on our experiments and first results on building a framenet to cover the terms and concepts encountered in descriptive linguistic grammars. A contextual statistics based approach is used to judge the polysemous nature of domain-specific terms, and to design new domain-specific frames. The work is part of a more extensive research undertaking where we are developing NLP methodologies for automatic extraction of linguistic information from traditional linguistic descriptions to build typological databases, which otherwise are populated using a labor intensive
manual process.},
	booktitle    = {Proceedings : LREC 2018 Workshop, International FrameNet Workshop 2018. Multilingual Framenets and Constructicons, May 12, 2018, Miyazaki, Japan / Edited by Tiago Timponi Torrent, Lars Borin and Collin F. Baker},
	author       = {Malm, Per and Virk, Shafqat and Borin, Lars and Saxena, Anju},
	year         = {2018},
	publisher    = {ELRA},
	address      = {Miyazaki},
	ISBN         = {979-10-95546-04-7},
}

@misc{torrent-etal-2018-proceedings-267405,
	title        = {Proceedings of the LREC 2018 Workshop International FrameNet Workshop 2018: Multilingual Framenets and Constructicons. 12 May 2018 – Miyazaki, Japan},
	abstract     = {The International FrameNet Workshop 2018 brought together researchers in Frame Semantics and Construction Grammar, two areas which have traditionally been interrelated, but which have been developing somewhat independently in recent years. It is also addressed at language technology researchers working with language resources based on Frame Semantics or Construction Grammar. The workshop follows on from similar joint meetings in Berkeley, California in 2013 (IFNW 2013, sponsored by the Swedish FrameNet group) and in Juiz de Fora, Brazil in 2016 (IFNW 2016, sponsored by FrameNet Brasil), and will cover the rapidly unfolding developments in both areas and recent research on their interconnections.},
	author       = {Torrent, Tiago Timponi and Borin, Lars and Baker, Collin},
	year         = {2018},
	publisher    = {ELRA},
	address      = {Miyazaki},
	ISBN         = {979-10-95546-04-7},
}

@inProceedings{borin-etal-2018-many-267534,
	title        = {Many a little makes a mickle - infrastructure component reuse for a massively multilingual linguistic study},
	abstract     = {We present ongoing work aiming at turning the linguistic material available in Grierson’s classical Linguistic Survey of India (LSI) into a digital language resource, a database suitable for a broad array of linguistic investigations of the languages of South Asia and studies relating to language typology and contact linguistics. The project has two concrete main aims: (1) to conduct a linguistic investigation of the claim that South Asia constitutes a linguistic area; (2) to develop state-of-the-art language technology for automatically extracting the relevant information from the text of the LSI. In this presentation we focus on how, in the first part of the project, a number of existing research infrastructure components provided by Swe-Clarin, the Swedish CLARIN consortium, have been ‘recycled’ in order to allow the linguists involved in the project to quickly orient themselves in the vast LSI material, and to be able to provide input to the language technologists designing the tools for information extraction from the descriptive grammars.},
	booktitle    = {Selected papers from the CLARIN Annual Conference 2017, Budapest, 18–20 September 2017},
	author       = {Borin, Lars and Virk, Shafqat and Saxena, Anju},
	year         = {2018},
	publisher    = {Linköping University Electronic Press},
	address      = {Linköping},
	ISBN         = {978-91-7685-273-6},
}

@inProceedings{karsvall-borin-2018-sdhk-265603,
	title        = {SDHK meets NER: Linking place names with medieval charters and historical maps},
	booktitle    = {CEUR Workshop Proceedings, vol. 2084.  Proceedings of the Digital Humanities in the Nordic Countries 3rd Conference Helsinki, Finland, March 7-9, 2018.  Edited by  Eetu Mäkelä Mikko Tolonen Jouni Tuominen },
	author       = {Karsvall, Olof and Borin, Lars},
	year         = {2018},
	publisher    = {University of Helsinki, Faculty of Arts},
	address      = {Helsinki},
}