@inproceedings{siewert-rueter-2024-low-saxon,
title = "The {L}ow {S}axon {LSDC} Dataset at {U}niversal {D}ependencies",
author = "Siewert, Janine and
Rueter, Jack",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1388",
pages = "15976--15981",
abstract = "We present an extension of the Low Saxon Universal Dependencies dataset and discuss a few annotation-related challenges. Low Saxon is a West-Germanic low-resource language that lacks a common standard and therefore poses challenges for NLP. The 1,000 sentences in our dataset cover the last 200 years and 8 of the 9 major dialects. They are presented both in original and in normalised spelling and two lemmata are provided: A Modern Low Saxon lemma and a Middle Low Saxon lemma. Several annotation-related issues result from dialectal variation in morphological categories, and we explain differences in the pronoun, gender, case, and mood system. Furthermore, we take up three syntactic constructions that do not occur in Standard Dutch or Standard German: the possessive dative, pro-drop in pronominal adverbs, and complementiser doubling in subordinate interrogative clauses. These constructions are also rare in the other Germanic UD datasets and have not always been annotated consistently.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="siewert-rueter-2024-low-saxon">
<titleInfo>
<title>The Low Saxon LSDC Dataset at Universal Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janine</namePart>
<namePart type="family">Siewert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Rueter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present an extension of the Low Saxon Universal Dependencies dataset and discuss a few annotation-related challenges. Low Saxon is a West-Germanic low-resource language that lacks a common standard and therefore poses challenges for NLP. The 1,000 sentences in our dataset cover the last 200 years and 8 of the 9 major dialects. They are presented both in original and in normalised spelling and two lemmata are provided: A Modern Low Saxon lemma and a Middle Low Saxon lemma. Several annotation-related issues result from dialectal variation in morphological categories, and we explain differences in the pronoun, gender, case, and mood system. Furthermore, we take up three syntactic constructions that do not occur in Standard Dutch or Standard German: the possessive dative, pro-drop in pronominal adverbs, and complementiser doubling in subordinate interrogative clauses. These constructions are also rare in the other Germanic UD datasets and have not always been annotated consistently.</abstract>
<identifier type="citekey">siewert-rueter-2024-low-saxon</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1388</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>15976</start>
<end>15981</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The Low Saxon LSDC Dataset at Universal Dependencies
%A Siewert, Janine
%A Rueter, Jack
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F siewert-rueter-2024-low-saxon
%X We present an extension of the Low Saxon Universal Dependencies dataset and discuss a few annotation-related challenges. Low Saxon is a West-Germanic low-resource language that lacks a common standard and therefore poses challenges for NLP. The 1,000 sentences in our dataset cover the last 200 years and 8 of the 9 major dialects. They are presented both in original and in normalised spelling and two lemmata are provided: A Modern Low Saxon lemma and a Middle Low Saxon lemma. Several annotation-related issues result from dialectal variation in morphological categories, and we explain differences in the pronoun, gender, case, and mood system. Furthermore, we take up three syntactic constructions that do not occur in Standard Dutch or Standard German: the possessive dative, pro-drop in pronominal adverbs, and complementiser doubling in subordinate interrogative clauses. These constructions are also rare in the other Germanic UD datasets and have not always been annotated consistently.
%U https://aclanthology.org/2024.lrec-main.1388
%P 15976-15981
Markdown (Informal)
[The Low Saxon LSDC Dataset at Universal Dependencies](https://aclanthology.org/2024.lrec-main.1388) (Siewert & Rueter, LREC-COLING 2024)
ACL
- Janine Siewert and Jack Rueter. 2024. The Low Saxon LSDC Dataset at Universal Dependencies. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 15976–15981, Torino, Italia. ELRA and ICCL.