1. |
- Adesam, Yvonne, 1975, et al.
(author)
-
Computer-aided Morphology Expansion for Old Swedish
- 2014
-
In: Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14) May 26-31, 2014 Reykjavik, Iceland. - 9782951740884 ; , s. 1102-1105
-
Conference paper (peer-reviewed)abstract
- In this paper we describe and evaluate a tool for paradigm induction and lexicon extraction that has been applied to Old Swedish. The tool is semi-supervised and uses a small seed lexicon and unannotated corpora to derive full inflection tables for input lemmata. In the work presented here, the tool has been modified to deal with the rich spelling variation found in Old Swedish texts. We also present some initial experiments, which are the first steps towards creating a large-scale morphology for Old Swedish.
|
|
2. |
- Adesam, Yvonne, 1975, et al.
(author)
-
Språkteknologi för svenska språket genom tiderna
- 2016
-
In: Kungliga Skytteanska Samfundets Handlingar. - Umeå : Institutionen för språkstudier, Umeå universitet & Kungl. Skytteanska Samfundet. - 0560-2416. ; 76:Studier i svensk språkhistoria 13, s. 65-87, s. 65-87
-
Journal article (peer-reviewed)abstract
- Språkbanken, the Swedish Language Bank, is a language technology research unit at the Department of Swedish, University of Gothenburg. We develop language resources – such as corpora, lexical resources, and analytical tools – for all variants of Swedish, from Old Swedish laws to present-day social media. Historical texts offer exciting theoretical and methodological challenges for language technology because they often defy the assumption inherent in most automatic analysis tools that the texts contain a standardized written language. In this article, we describe our ongoing work on the development of annotated historical corpora, as well as our efforts on linking various resources (both corpora and lexical resources). This research advances the state of the art of language technology as well as enables new research for scholars in other disciplines.
|
|
3. |
- Ahlberg, Malin, 1986, et al.
(author)
-
A case study on supervised classification of Swedish pseudo-coordination
- 2015
-
In: Proceedings of the 20th Nordic Conference of Computational Linguistics, NODALIDA 2015, May 11-13, 2015, Vilnius, Lithuania. - Linköpings universitet : Linköping University Electronic Press. - 1650-3686 .- 1650-3740. - 9789175190983
-
Conference paper (peer-reviewed)abstract
- We present a case study on supervised classification of Swedish pseudo-coordination (SPC). The classification is attempted on the type-level with data collected from two data sets: a blog corpus and a fiction corpus. Two small experiments were designed to evaluate the feasability of this task. The first experiment explored a classifier’s ability to discriminate pseudo-coordinations from ordinary verb coordinations, given a small labeled data set created during the experiment. The second experiment evaluated how well the classifier performed at detecting and ranking SPCs in a set of unlabeled verb coordinations, to investigate if it could be used as a semi-automatic discovery procedure to find new SPCs.
|
|
4. |
|
|
5. |
- Lyngfelt, Benjamin, 1968, et al.
(author)
-
Adding a constructicon to the Swedish resource network of Språkbanken
- 2012
-
In: 11th Conference on Natural Language Processing (KONVENS) Proceedings. - 385027005X ; , s. 452-461
-
Conference paper (peer-reviewed)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.
|
|
6. |
- Lyngfelt, Benjamin, 1968, et al.
(author)
-
Ett svenskt konstruktikon. Grammatik möter lexikon
- 2014
-
In: Svenskans beskrivning : Förhandlingar vid Trettiotredje sammankomsten för svenskans beskrivning. Helsingfors den 15–17 maj 2013. - 1795-4428. - 9789515101204 ; 33, s. 268-279, s. 268-279
-
Conference paper (peer-reviewed)
|
|
7. |
- Sköldberg, Emma, 1968, et al.
(author)
-
Between Grammars and Dictionaries: a Swedish Constructicon
- 2013
-
In: Kosem, I., Kallas, J., Gantar, P., Krek, S., Langemets, M., Tuulik, M. (eds.) 2013. Electronic lexicography in the 21st century: thinking outside the paper. Proceedings of the eLex 2013 conference, 17-19 October 2013, Tallinn, Estonia. Ljubljana/Tallinn: Trojina, Institute for Applied Slovene Studies/Eesti Keele Instituut.. ; , s. 310-327, s. 310-327
-
Conference paper (other academic/artistic)abstract
- This paper introduces the Swedish Constructicon (SweCxn), a database of Swedish constructions currently under development. We also present a small study of the treatment of constructions in Swedish (paper) dictionaries, thus illustrating the need for a constructionist approach, and discuss three different methods used to identify potential constructions for inclusion in the constructicon. SweCxn is a freely available electronic resource, with a particular focus on semi-general linguistic patterns of the type that are difficult to account for from a purely lexicographic or a purely grammatical perspective, and which therefore have tended to be neglected in both dictionaries and grammars. Far from being a small set of borderline cases, such constructions are both numerous and common. They are also quite problematic for second language acquisition as well as LT applications. Accordingly, various kinds of multi-word units have received more attention in recent years, not least from a lexicographic perspective. The coverage, however, is only partial, and the productivity of many constructions is hard to capture from a lexical viewpoint. To identify constructions for SweCxn, we use a combination of methods, such as working from existing construction descriptions for Swedish and other languages, applying LT tools to discover recurring patterns in texts, and extrapolating constructional information from dictionaries.
|
|
8. |
|
|
9. |
- Adesam, Yvonne, 1975, et al.
(author)
-
The Eukalyptus Treebank of Written Swedish
- 2018
-
In: Seventh Swedish Language Technology Conference (SLTC), Stockholm, 7–9 November 2018.
-
Conference paper (other academic/artistic)
|
|
10. |
|
|
11. |
- Ahlberg, Malin, 1986, et al.
(author)
-
Korp and Karp – a bestiary of language resources: the research infrastructure of Språkbanken
- 2013
-
In: Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013), May 22–24, 2013, Oslo University, Norway. NEALT Proceedings Series 16. - Linköping : Linköping University Electronic Press. - 1650-3686 .- 1650-3740.
-
Conference paper (peer-reviewed)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.
|
|
12. |
- Ahlberg, Malin, 1986, et al.
(author)
-
Paradigm classification in supervised learning of morphology
- 2015
-
In: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.
-
Conference paper (peer-reviewed)abstract
- Supervised morphological paradigm learning by identifying and aligning the longest common subsequence found in inflection tables has recently been proposed as a simple yet competitive way to induce morphological patterns. We combine this non-probabilistic strategy of inflection table generalization with a discriminative classifier to permit the reconstruction of complete inflection tables of unseen words. Our system learns morphological paradigms from labeled examples of inflection patterns (inflection tables) and then produces inflection tables from unseen lemmas or base forms. We evaluate the approach on datasets covering 11 different languages and show that this approach results in consistently higher accuracies vis-a-vis other methods on the same task, thus indicating that the general method is a viable approach to quickly creating high-accuracy morphological resources.
|
|
13. |
- Ahlberg, Malin, 1986, et al.
(author)
-
Semi-supervised learning of morphological paradigms and lexicons
- 2014
-
In: Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics, Gothenburg, Sweden 26–30 April 2014. - 9781937284787 ; , s. 569-578
-
Conference paper (peer-reviewed)abstract
- We present a semi-supervised approach to the problem of paradigm induction from inflection tables. Our system extracts generalizations from inflection tables, representing the resulting paradigms in an abstract form. The process is intended to be language-independent, and to provide human-readable generalizations of paradigms. The tools we provide can be used by linguists for the rapid creation of lexical resources. We evaluate the system through an inflection table reconstruction task using Wiktionary data for German, Spanish, and Finnish. With no additional corpus information available, the evaluation yields per word form accuracy scores on inflecting unseen base forms in different lan guages ranging from 87.81% (German nouns) to 99.52% (Spanish verbs); with additional unlabeled tex t corpora available for training the scores range from 91.81% (German nouns) to 99.58% (Spanish verbs). We separately evaluate the system in a simulated task of Swedish lexicon creation, and show that on the basis of a small number of inflection tables, the system can accurately collect from a list of noun forms a lexicon with inflection information ranging from 100.0% correct (collect 100 words), to 96.4% correct (collect 1000 words).
|
|
14. |
- Ahlberg, Malin, 1986, et al.
(author)
-
Språkbanken’s Open Lexical Infrastructure
- 2016
-
In: SLTC 2016. The Sixth Swedish Language Technology Conference. Umeå University, 17-18 November, 2016.
-
Conference paper (other academic/artistic)abstract
- Karp is an open lexical infrastructure and a web based tool for searching, exploring and developing lexical resources. Språkbanken currently hosts a number of lexicons in Karp and on-going work aims at broadening the type of resources that can be developed in the system. This abstract gives a short overview of Karp's basic functionality, and describes some current projects and on-going work.
|
|
15. |
|
|
16. |
- Andersen, Christiane, 1951, et al.
(author)
-
Sibirientyska : German in Siberia
- 2012
-
In: http://spraakbanken.gu.se/korp/ Links. - Göteborg : University of Gothenburg.
-
Other publication (other academic/artistic)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.
|
|
17. |
- Andersen, Christiane, 1951, et al.
(author)
-
Sibirientyska kvinnor (Siberian German women) : digitalt korpus
- 2015
-
In: Korp. Språkbankens konkordansverktyg. - Göteborg : University of Gothenburg.
-
Other publication (other academic/artistic)abstract
- Siberian German women The corpus consists of dialogs between four women born in 1927 to 1937 in the Soviet Volga Republic. Their mother tongue is a German variety spoken in Russia since the second half of the 18th century. Since the end of the Second World War, the women have lived in the region of Krasnoyarsk. They talk about their backgrounds and their everyday lives in the village. The corpus consists of about 16 000 words. Russian words and hybrids are given in [brackets], the turns of the interviewers are in {brackets}; all verb forms have got the attribute FINIT or INFINIT. More information on the research project see Syntax in contact.
|
|
18. |
- Andréasson, Maia, 1960, et al.
(author)
-
Swedish CLARIN activities
- 2009
-
In: Proceedings of the Nodalida 2009 workshop on CLARIN activities in the Nordic countries. NEALT Proceedings Series. - 1736-6305. ; 5, s. 1-5
-
Conference paper (peer-reviewed)
|
|
19. |
- Berdicevskis, Aleksandrs, 1983, et al.
(author)
-
Superlim: A Swedish Language Understanding Evaluation Benchmark
- 2023
-
In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, December 6-10, 2023, Singapore / Houda Bouamor, Juan Pino, Kalika Bali (Editors). - Stroudsburg, PA : Association for Computational Linguistics. - 9798891760608
-
Conference paper (peer-reviewed)
|
|
20. |
|
|
21. |
- Borin, Lars, 1957, et al.
(author)
-
All in the family: A comparison of SALDO and WordNet
- 2009
-
In: Proceedings of the Nodalida 2009 Workshop on WordNets and other Lexical Semantic Resources - between Lexical Semantics, Lexicography, Terminology and Formal Ontologies. NEALT Proceedings Series. - 1736-6305. ; 7
-
Conference paper (peer-reviewed)
|
|
22. |
|
|
23. |
- Borin, Lars, 1957, et al.
(author)
-
Close encounters of the fifth kind: Some linguistic and computational aspects of the Swedish FrameNet++ project
- 2013
-
In: Veredas. - 1415-2533 .- 1982-2243. ; 17:1, s. 28-43
-
Journal article (peer-reviewed)abstract
- The Swedish FrameNet++ (SweFN++) project aims at developing an integrated Swedish lexical macro-resource to be used primarily in language technology R&D to build natural language processing (NLP) applications. Most of the component resources making up SweFN++ are existing digital lexical resources; in their case the central project effort is directed at making them interoperable on as many levels as possible. An important new resource being created in the project is a Swedish framenet. Now a sister project is starting with the aim of adding a Swedish constructicon (SweCxn) to the macro-resource. In this paper, we discuss some theoretical and conceptual issues which have arisen in the course of our work on the SweFN++ and the planning of the SweCxn, in the close encounter between the practical requirements of NLP and the theory and practice of linguistic – lexical and grammatical – description.
|
|
24. |
|
|
25. |
|
|