The Seemingly (Un)systematic Linking Element in Danish

Publikation: Bidrag til tidsskriftKonferenceartikelForskningfagfællebedømt

Standard

The Seemingly (Un)systematic Linking Element in Danish. / Boldsen, Sidsel; Aguirrezabal Zabaleta, Manex.

I: NEALT (Northern European Association of Language Technology) Monograph Series, Bind 42, 10.2019, s. 376-380.

Publikation: Bidrag til tidsskriftKonferenceartikelForskningfagfællebedømt

Harvard

Boldsen, S & Aguirrezabal Zabaleta, M 2019, 'The Seemingly (Un)systematic Linking Element in Danish', NEALT (Northern European Association of Language Technology) Monograph Series, bind 42, s. 376-380. <https://www.aclweb.org/anthology/W19-61.pdf>

APA

Boldsen, S., & Aguirrezabal Zabaleta, M. (2019). The Seemingly (Un)systematic Linking Element in Danish. NEALT (Northern European Association of Language Technology) Monograph Series, 42, 376-380. https://www.aclweb.org/anthology/W19-61.pdf

Vancouver

Boldsen S, Aguirrezabal Zabaleta M. The Seemingly (Un)systematic Linking Element in Danish. NEALT (Northern European Association of Language Technology) Monograph Series. 2019 okt.;42:376-380.

Author

Boldsen, Sidsel ; Aguirrezabal Zabaleta, Manex. / The Seemingly (Un)systematic Linking Element in Danish. I: NEALT (Northern European Association of Language Technology) Monograph Series. 2019 ; Bind 42. s. 376-380.

Bibtex

@inproceedings{078b6a18f1de4903b63dc95f60f0c80e,
title = "The Seemingly (Un)systematic Linking Element in Danish",
abstract = "The use of a linking element between compound members is a common phenomenon in Germanic languages. Still, the exact use and conditioning of such elements is a disputed topic in linguistics. In this paper we address the issue of predicting the use of linking elements in Danish. Following previous research that shows how the choice of linking element might be conditioned by phonology, we frame the problem as a language modeling task: Considering the linking elements -s/-∅ the problem becomes predicting what is most probable to encounter next, a syllable boundary or the joining element, s. We show that training a language model on this task reaches an accuracy of 94 %, and in the case of an unsupervised model, the accuracy reaches 80 %.",
author = "Sidsel Boldsen and {Aguirrezabal Zabaleta}, Manex",
year = "2019",
month = oct,
language = "English",
volume = "42",
pages = "376--380",
journal = "NEALT (Northern European Association of Language Technology) Monograph Series",
issn = "1736-6291",

}

RIS

TY - GEN

T1 - The Seemingly (Un)systematic Linking Element in Danish

AU - Boldsen, Sidsel

AU - Aguirrezabal Zabaleta, Manex

PY - 2019/10

Y1 - 2019/10

N2 - The use of a linking element between compound members is a common phenomenon in Germanic languages. Still, the exact use and conditioning of such elements is a disputed topic in linguistics. In this paper we address the issue of predicting the use of linking elements in Danish. Following previous research that shows how the choice of linking element might be conditioned by phonology, we frame the problem as a language modeling task: Considering the linking elements -s/-∅ the problem becomes predicting what is most probable to encounter next, a syllable boundary or the joining element, s. We show that training a language model on this task reaches an accuracy of 94 %, and in the case of an unsupervised model, the accuracy reaches 80 %.

AB - The use of a linking element between compound members is a common phenomenon in Germanic languages. Still, the exact use and conditioning of such elements is a disputed topic in linguistics. In this paper we address the issue of predicting the use of linking elements in Danish. Following previous research that shows how the choice of linking element might be conditioned by phonology, we frame the problem as a language modeling task: Considering the linking elements -s/-∅ the problem becomes predicting what is most probable to encounter next, a syllable boundary or the joining element, s. We show that training a language model on this task reaches an accuracy of 94 %, and in the case of an unsupervised model, the accuracy reaches 80 %.

M3 - Conference article

VL - 42

SP - 376

EP - 380

JO - NEALT (Northern European Association of Language Technology) Monograph Series

JF - NEALT (Northern European Association of Language Technology) Monograph Series

SN - 1736-6291

ER -

ID: 238738445