@inproceedings{aoyama-etal-2024-j,
title = "{J}-{SNACS}: Adposition and Case Supersenses for {J}apanese Joshi",
author = "Aoyama, Tatsuya and
Taguchi, Chihiro and
Schneider, Nathan",
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.839",
pages = "9604--9614",
abstract = "Many languages use adpositions (prepositions or postpositions) to mark a variety of semantic relations, with different languages exhibiting both commonalities and idiosyncrasies in the relations grouped under the same lexeme. We present the first Japanese extension of the SNACS framework (Schneider et al., 2018), which has served as the basis for annotating adpositions in corpora from several languages. After establishing which of the set of particles (joshi) in Japanese qualify as case markers and adpositions as defined in SNACS, we annotate 10 chapters ({\mbox{$\approx$}}10k tokens) of the Japanese translation of Le Petit Prince (The Little Prince), achieving high inter-annotator agreement. We find that, while a majority of the particles and their uses are captured by the existing and extended SNACS annotation guidelines from the previous work, some unique cases were observed. We also conduct experiments investigating the cross-lingual similarity of adposition and case marker supersenses, showing that the language-agnostic SNACS framework captures similarities not clearly observed in multilingual embedding space.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="aoyama-etal-2024-j">
<titleInfo>
<title>J-SNACS: Adposition and Case Supersenses for Japanese Joshi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Aoyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chihiro</namePart>
<namePart type="family">Taguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</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>Many languages use adpositions (prepositions or postpositions) to mark a variety of semantic relations, with different languages exhibiting both commonalities and idiosyncrasies in the relations grouped under the same lexeme. We present the first Japanese extension of the SNACS framework (Schneider et al., 2018), which has served as the basis for annotating adpositions in corpora from several languages. After establishing which of the set of particles (joshi) in Japanese qualify as case markers and adpositions as defined in SNACS, we annotate 10 chapters (\approx10k tokens) of the Japanese translation of Le Petit Prince (The Little Prince), achieving high inter-annotator agreement. We find that, while a majority of the particles and their uses are captured by the existing and extended SNACS annotation guidelines from the previous work, some unique cases were observed. We also conduct experiments investigating the cross-lingual similarity of adposition and case marker supersenses, showing that the language-agnostic SNACS framework captures similarities not clearly observed in multilingual embedding space.</abstract>
<identifier type="citekey">aoyama-etal-2024-j</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.839</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9604</start>
<end>9614</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T J-SNACS: Adposition and Case Supersenses for Japanese Joshi
%A Aoyama, Tatsuya
%A Taguchi, Chihiro
%A Schneider, Nathan
%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 aoyama-etal-2024-j
%X Many languages use adpositions (prepositions or postpositions) to mark a variety of semantic relations, with different languages exhibiting both commonalities and idiosyncrasies in the relations grouped under the same lexeme. We present the first Japanese extension of the SNACS framework (Schneider et al., 2018), which has served as the basis for annotating adpositions in corpora from several languages. After establishing which of the set of particles (joshi) in Japanese qualify as case markers and adpositions as defined in SNACS, we annotate 10 chapters (\approx10k tokens) of the Japanese translation of Le Petit Prince (The Little Prince), achieving high inter-annotator agreement. We find that, while a majority of the particles and their uses are captured by the existing and extended SNACS annotation guidelines from the previous work, some unique cases were observed. We also conduct experiments investigating the cross-lingual similarity of adposition and case marker supersenses, showing that the language-agnostic SNACS framework captures similarities not clearly observed in multilingual embedding space.
%U https://aclanthology.org/2024.lrec-main.839
%P 9604-9614
Markdown (Informal)
[J-SNACS: Adposition and Case Supersenses for Japanese Joshi](https://aclanthology.org/2024.lrec-main.839) (Aoyama et al., LREC-COLING 2024)
ACL
- Tatsuya Aoyama, Chihiro Taguchi, and Nathan Schneider. 2024. J-SNACS: Adposition and Case Supersenses for Japanese Joshi. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9604–9614, Torino, Italia. ELRA and ICCL.