Question-parsing with Abstract Meaning Representation enhanced by adding small datasets

Lühendatud kirje lehekülg
dc.contributor.authorHeinecke, Johannes
dc.contributor.authorBoritchev, Maria
dc.contributor.authorHerledan, Frédéric
dc.contributor.editorJohansson, Richard
dc.contributor.editorStymne, Sara
dc.coverage.spatialTallinn, Estonia
dc.date.accessioned2025-02-18T09:05:55Z
dc.date.available2025-02-18T09:05:55Z
dc.date.issued2025-03
dc.description.abstractAbstract Meaning Representation (AMR) is a graph-based formalism for representing meaning in sentences. As the annotation is quite complex, few annotated corpora exist. The most well-known and widely-used corpora are LDC’s AMR 3.0 and the datasets available on the new AMR website. Models trained on the LDC corpora work fine on texts with similar genre and style: sentences extracted from news articles, Wikipedia articles. However, other types of texts, in particular questions, are less well processed by models trained on this data. We analyse how adding few sentence-type specific annotations can steer the model to improve parsing in the case of questions in English.
dc.identifier.urihttps://hdl.handle.net/10062/107217
dc.language.isoen
dc.publisherUniversity of Tartu Library
dc.relation.ispartofseriesNEALT Proceedings Series, No. 57
dc.rightsAttribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.titleQuestion-parsing with Abstract Meaning Representation enhanced by adding small datasets
dc.typeArticle

Failid

Originaal pakett

Nüüd näidatakse 1 - 1 1
Pisipilt
Nimi:
2025_nodalida_1_26.pdf
Suurus:
125.43 KB
Formaat:
Adobe Portable Document Format
Lae alla

Kollektsioonid

Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025)