Synthetic-Error Augmented Parsing of Swedish as a Second Language: Experiments with Word Order

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F25%3AQ45IXFCI" target="_blank" >RIV/00216208:11320/25:Q45IXFCI - isvavai.cz</a>

Výsledek na webu

<a href="https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195172772&partnerID=40&md5=a144a8a927993680fe5bd6490c7760cf" target="_blank" >https://www.scopus.com/inward/record.uri?eid=2-s2.0-85195172772&partnerID=40&md5=a144a8a927993680fe5bd6490c7760cf</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Synthetic-Error Augmented Parsing of Swedish as a Second Language: Experiments with Word Order

Popis výsledku v původním jazyce

Ungrammatical text poses significant challenges for off-the-shelf dependency parsers. In this paper, we explore the effectiveness of using synthetic data to improve performance on essays written by learners of Swedish as a second language. Due to their relevance and ease of annotation, we restrict our initial experiments to word order errors. To do that, we build a corrupted version of the standard Swedish Universal Dependencies (UD) treebank Talbanken, mimicking the error patterns and frequency distributions observed in the Swedish Learner Language (SweLL) corpus. We then use the MaChAmp (Massive Choice, Ample tasks) toolkit to train an array of BERT-based dependency parsers, fine-tuning on different combinations of original and corrupted data. We evaluate the resulting models not only on their respective test sets but also, most importantly, on a smaller collection of sentence-correction pairs derived from SweLL. Results show small but significant performance improvements on the target domain, with minimal decline on normative data. © European Language Resources Association: CC BY-NC 4.0.

Název v anglickém jazyce

Synthetic-Error Augmented Parsing of Swedish as a Second Language: Experiments with Word Order

Popis výsledku anglicky

Ungrammatical text poses significant challenges for off-the-shelf dependency parsers. In this paper, we explore the effectiveness of using synthetic data to improve performance on essays written by learners of Swedish as a second language. Due to their relevance and ease of annotation, we restrict our initial experiments to word order errors. To do that, we build a corrupted version of the standard Swedish Universal Dependencies (UD) treebank Talbanken, mimicking the error patterns and frequency distributions observed in the Swedish Learner Language (SweLL) corpus. We then use the MaChAmp (Massive Choice, Ample tasks) toolkit to train an array of BERT-based dependency parsers, fine-tuning on different combinations of original and corrupted data. We evaluate the resulting models not only on their respective test sets but also, most importantly, on a smaller collection of sentence-correction pairs derived from SweLL. Results show small but significant performance improvements on the target domain, with minimal decline on normative data. © European Language Resources Association: CC BY-NC 4.0.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2024

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Jt. Workshop Multiword Expressions Univers. Depend., MWE-UD LREC-COLING - Workshop Proc.

ISBN

978-249381420-3

ISSN

—

e-ISSN

—

Počet stran výsledku

7

Strana od-do

43-49

Název nakladatele

European Language Resources Association (ELRA)

Místo vydání

—

Místo konání akce

Torino, Italia

Datum konání akce

1. 1. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—