• Fra partikkelverb og preposisjoner til verbavledninger og kasus. Brukerstudie av ei nordsamisk-norsk-nordsamisk ordbok 

      Dominczak, Katarzyna Zofia; Antonsen, Lene; Trosterud, Trond (Journal article; Tidsskriftartikkel; Peer reviewed, 2022-11-29)
      The article discusses challenges facing the bidirectional North Saami–Norwegian e-dictionary Neahttadigisánit when used as a production dictionary, based upon a set of writing and translation tasks presented to second term students and logging of their dictionary use. The dictio¬nary's ability to both analyse and generate Norwegian and Saami forms is of great help to the students. The dictionary ...
    • The GiellaLT infrastructure: A multilingual infrastructure for rule-based NLP 

      Nørstebø Moshagen, Sjur; Pirinen, Flammie; Antonsen, Lene; Gaup, Børre; Mikkelsen, Inga Lill Sigga; Trosterud, Trond; Wiechetek, Linda; Hiovain-Asikainen, Katri (Journal article; Tidsskriftartikkel; Peer reviewed, 2023)
      This article gives an overview of the GiellaLT infrastructure, the main parts of it, and how it has been and can be used to support a large number of indigenous and minority languages, from keyboards to speech technology and advanced proofing tools. A special focus is given to languages with few or non-existing digital resources, and it is shown that many tools useful to the daily digital life of ...
    • Hva er viktig for forståelse? Om maskinoversetting fra nordsamisk 

      Trosterud, Trond; Antonsen, Lene (Journal article; Tidsskriftartikkel; Peer reviewed, 2021-01-22)
      Artikkelen presenterer et regelbasert maskinoversettingssystem fra nordsamisk til norsk. Den grammatiske analysen blir gjort med Giellatekno og Divvuns nord-samiske analyseprogram. Vi har skrevet transferkomponenten (transferleksikon og grammatiske regler) innafor rammeverket til det åpne maskinoversettings-systemet Apertium. Artikkelen inneholder ei evaluering av oversatt tekst for to ulike domener. ...
    • Kva bruker vi minoritetsspråksordbøker til? Ein studie av brukarloggane for tolv tospråklege ordbøker 

      Trosterud, Trond (Journal article; Tidsskriftartikkel; Peer reviewed, 2019-11-27)
      The article analyses the user logs of twelve different bilingual mi- nority language dictionaries. The logs show that the dictionaries are in frequent use, with lookup in the direction towards the minor- ity language (production use) dominating by approximately 60% of the total queries. Query recall is high, around 90%, despite the dictionaries being medium-size to small, and most failed queries are ...
    • Normative language work in the age of machine learning 

      Trosterud, Trond (Chapter; Bokkapittel, 2021)
      Neural nets have, during the last few years, given us both an improved Google Translate, better search algorithms, better speech technology and doubtless many other things. The approach dominates current language technology to the extent that no other approach is visible. Being data driven, the hidden assumption behind this approach when used in proofing tools is that the language is used correctly ...
    • Ord sett innafra og utafra – en datalingvistisk analyse av nordsamisk 

      Antonsen, Lene; Trosterud, Trond (Journal article; Tidsskriftartikkel; Peer reviewed, 2017)
      Artikkelen presenterer et analyseprogram for nordsamisk løpende tekst, bestående av en morfologisk transduser og en føringsgrammatikk for disambiguering og syntaktisk analyse. Artikkelen drøfter hva programmet kan fortelle oss om nordsamisk grammatikk når det brukes til å analysere et nordsamisk tekstkorpus bestående av til sammen 25 millioner ord. Vi ser på produktiviteten for en del sentrale ...
    • Partiklar i sørsamisk 

      Trosterud, Trond (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-08-30)
      The article presents the most central particles in Southern Sami, and argues that they constitute a separate part of speech different from adverbs. Most particles usually occur in the second position of the sentence, but several particles may also occur in second position in complex verb phrases, i.e. in third position in the sentence. A group of words have in previous research been treated as ...
    • A restricted freedom of choice: Linguistic diversity in the digital landscape 

      Trosterud, Trond (Journal article; Tidsskriftartikkel; Peer reviewed, 2012)
      The freedom of choosing what language to use in various contexts is restricted by a wide range of non-linguistic factors. One often-overlooked factor is the availability of a digital infrastructure for the languages in question. To put it bluntly: With no keyboard layout available there also will be no texts written. The article looks at different aspects related to minority languages and digital ...
    • Samisk: láibi og gáhkku 

      Antonsen, Lene; Trosterud, Trond (Conference object; Konferansebidrag, 2022)
    • Strengthening the Literacy of an Indigenous Language Community: Methodological Implications of the Project Čyeti čälled anaraškielân, 'One Hundred writers for Aanaar Saami' 

      Olthuis, Marja-Liisa; Trosterud, Trond; Sarivaara, Erika Katjaana; Morottaja, Petter; Niskanen, Eljas (Chapter; Bokkapittel, 2021-05-03)
      Aanaar Saami literacy is weaker than majority languages, in the sense that reading and writing Aanaar Saami is less common. In order to strengthen literacy, we argue for an approach that represents a methodology for participatory research from a community and from an in-group perspective. We also discuss the implications this has for indigenous research. The article presents a strategy for producing ...
    • Suoidne-varra-bleahkka-mála-bihkka-senet-dielku 'hay-blood-ink-paint-tar-mustard-stain' -Should compounds be lexicalized in NLP? 

      Wiechetek, Linda; Argese, Chiara; Pirinen, Tommi; Trosterud, Trond (Journal article; Tidsskriftartikkel, 2020-12-11)
      Lexicalizing compounds, in addition to treating them dynamically, is a key element in giving us idiomatic translations and detecting compound errors. We present and evaluate an e-dictionary (NDS) and a grammar checker (<i>GramDivvun</i>) for North Sámi. We achieve a coverage of 98% for NDSqueries and of 96% for compound error detection in <i>GramDivvun</i>.
    • Ulike veger fra nordsamisk til lulesamisk 

      Trosterud, Trond; Antonsen, Lene; Mikkelsen, Inga Lill Sigga; Lorentsen, Anders Viel (Journal article; Tidsskriftartikkel; Peer reviewed, 2023-11-28)
      The present article evaluates different approaches to the construc-tion of a North Saami-Lule Saami dictionary. The pivot method (via Norwegian) gives rise both to a low coverage and to a massive overgeneration and requires other methods in order to distinguish between good and bad candidate pairs. We show that it is possible to distinguish reliably between good and bad pairs ...