1. |
- Cap, Fabienne, et al.
(författare)
-
SWORD : Towards Cutting-Edge Swedish Word Processing
- 2016
-
Ingår i: Proceedings of SLTC 2016.
-
Konferensbidrag (refereegranskat)abstract
- Despite many years of research on Swedish language technology, there is still no well-documented standard for Swedish word processing covering the whole spectrum from low-level tokenization to morphological analysis and disambiguation. SWORD is a new initiative within the SWE-CLARIN consortium aiming to develop documented standards for Swedish word processing. In this paper, we report on a pilot study of Swedish tokenization, where we compare the output of six different tokenizers on four different text types. For one text type (Wikipedia articles), we also compare to the tokenization produced by six manual annotators.
|
|
2. |
|
|
3. |
- Pedersen, Bolette, et al.
(författare)
-
Nordic and Baltic wordnets aligned and compared through “WordTies”
- 2013
-
Ingår i: Proceedings of the 19th Nordic Conference of Computational Linguistics (NODALIDA 2013), May 22–24, 2013, Oslo University, Norway. NEALT Proceedings Series 16. - 1650-3686 .- 1650-3740. ; :16, s. 147-162
-
Konferensbidrag (refereegranskat)abstract
- During the last few years, extensive wordnets have been built locally for the Nordic and Baltic languages applying very different compilation strategies. The aim of the present investigation is to consolidate and examine these wordnets through an alignment via Princeton Core WordNet and thereby compare them along the measures of taxonomical structure, synonym structure, and assigned relations to approximate to a best practice. A common web interface and visualizer “WordTies” is developed to facilitate this purpose. Four bilingual wordnets are automatically processed and evaluated exposing interesting differences between the wordnets. Even if the alignments are judged to be of a good quality, the precision of the translations vary due to considerable differences in hyponymy depth and interpretation of the synset. All seven monolingual and four bilingual wordnets as well as WordTies have been made available via META-SHARE through the META-NORD project.
|
|
4. |
- Adesam, Yvonne, 1975, et al.
(författare)
-
A lexical resource for computational historical linguistics
- 2021
-
Ingår i: The Swedish FrameNet++. Harmonization, integration, method development and practical language technology applications. - Amsterdam / Philadelphia : John Benjamins Publishing Company. - 1567-8202. - 978 90 272 5848 9 ; , s. 98-121
-
Bokkapitel (refereegranskat)abstract
- In this chapter we present the diachronic dimension of Swedish FrameNet++. We describe the historical lexical resources currently available for Swedish, linked to the Contemporary Swedish lexicon Saldo. We present a case study of how interlinking the dictionaries simultaneously allows us to study lexical change. We also present a method of linking text words to lexicon entries, facilitating interactive exploration of historical texts. Diachronical language resources present both a high-variation challenge from a wider language technology perspective, and an interesting object of linguistic study. While a number of improvements of the parts of the diachronic lexical macroresource are still needed, this resource is invaluable for analysing and accessing historical texts, as well as for both synchronic historical and diachronic lexical studies.
|
|
5. |
|
|
6. |
- Adesam, Yvonne, 1975, et al.
(författare)
-
Språkteknologi för svenska språket genom tiderna
- 2016
-
Ingår i: 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
-
Tidskriftsartikel (refereegranskat)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.
|
|
7. |
- Adesam, Yvonne, 1975, et al.
(författare)
-
The Eukalyptus Treebank of Written Swedish
- 2018
-
Ingår i: Seventh Swedish Language Technology Conference (SLTC), Stockholm, 7–9 November 2018.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)
|
|
8. |
|
|
9. |
- Ahlberg, Malin, 1986, et al.
(författare)
-
Korp and Karp – a bestiary of language resources: the research infrastructure of Språkbanken
- 2013
-
Ingår i: 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.
-
Konferensbidrag (refereegranskat)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.
|
|
10. |
- Ahlberg, Malin, 1986, et al.
(författare)
-
Språkbanken’s Open Lexical Infrastructure
- 2016
-
Ingår i: SLTC 2016. The Sixth Swedish Language Technology Conference. Umeå University, 17-18 November, 2016.
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)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.
|
|