Other formats:
BibTeX
LaTeX
RIS
@inproceedings{1874319,
author = {Medková, Helena and Horák, Aleš},
address = {Amsterdam},
booktitle = {Towards a Knowledge-Aware AI : SEMANTiCS 2022 — Proceedings of the 18th International Conference on Semantic Systems, 13-15 September 2022, Vienna, Austria},
doi = {http://dx.doi.org/10.3233/SSW220022},
editor = {Dimou, Anastasia; Neumaier, Sebastian; Pellegrini, Tassilo; Vahdati, Sahar},
keywords = {natural language understanding; coordinated verbs with shared argument; zeugma; BERT language model; dataset},
howpublished = {tištěná verze "print"},
language = {eng},
location = {Amsterdam},
isbn = {978-1-64368-320-1},
pages = {206-218},
publisher = {IOS Press},
title = {Distinguishing the Types of Coordinated Verbs with a Shared Argument by means of New ZeugBERT Language Model and ZeugmaDataset},
url = {https://ebooks.iospress.nl/volumearticle/60724},
year = {2022}
}
TY - JOUR
ID - 1874319
AU - Medková, Helena - Horák, Aleš
PY - 2022
TI - Distinguishing the Types of Coordinated Verbs with a Shared Argument by means of New ZeugBERT Language Model and ZeugmaDataset
PB - IOS Press
CY - Amsterdam
SN - 9781643683201
KW - natural language understanding
KW - coordinated verbs with shared argument
KW - zeugma
KW - BERT language model
KW - dataset
UR - https://ebooks.iospress.nl/volumearticle/60724
N2 - Sentences where two verbs share a single argument represent a complex and highly ambiguous syntactic phenomenon. The argument sharing relations must be considered during the detection process from both a syntactic and semantic perspective. Such expressions can represent ungrammatical constructions, denoted as zeugma, or idiomatic elliptical phrase combinations. Rule-based classification methods prove ineffective because of the necessity to reflect meaning relations of the analyzed sentence constituents. This paper presents the development and evaluation of ZeugBERT, a language model tuned for the sentence classification task using a pre-trained Czech transformer model for language representation. The model was trained with a newly prepared dataset, which is also published with this paper, of 7,849 Czech sentences to classify Czech syntactic structures containing coordinated verbs that share a valency argument (or an optional adjunct) in the context of coordination. ZeugBERT here reaches $88\,\%$ of test set accuracy. The text describes the process of the new dataset creation and annotation, and it offers a detailed error analysis of the developed classification model.
ER -
MEDKOVÁ, Helena and Aleš HORÁK. Distinguishing the Types of Coordinated Verbs with a Shared Argument by means of New ZeugBERT Language Model and ZeugmaDataset. In Dimou, Anastasia; Neumaier, Sebastian; Pellegrini, Tassilo; Vahdati, Sahar. \textit{Towards a Knowledge-Aware AI : SEMANTiCS 2022 — Proceedings of the 18th International Conference on Semantic Systems, 13-15 September 2022, Vienna, Austria}. Amsterdam: IOS Press, 2022, p.~206-218. ISBN~978-1-64368-320-1. Available from: https://dx.doi.org/10.3233/SSW220022.
|
