PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging

0Citations
Citations of this article
45Readers
Mendeley users who have this article in their library.

Abstract

This paper describes PTST, a source-free unsupervised domain adaptation technique for sequence tagging, and its application to the SemEval-2021 Task 10 on time expression recognition. PTST is an extension of the cross-lingual parsimonious parser transfer framework (Kurniawan et al., 2021), which uses high-probability predictions of the source model as a supervision signal in self-training. We extend the framework to a sequence prediction setting, and demonstrate its applicability to unsupervised domain adaptation. PTST achieves F1 score of 79.6 % on the official test set, with the precision of 90.1 %, the highest out of 14 submissions.

References Powered by Scopus

Long Short-Term Memory

76783Citations
N/AReaders
Get full text

Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

13362Citations
N/AReaders
Get full text

Neural architectures for named entity recognition

2583Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Kurniawan, K., Frermann, L., Schulz, P., & Cohn, T. (2021). PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging. In SemEval 2021 - 15th International Workshop on Semantic Evaluation, Proceedings of the Workshop (pp. 445–451). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.semeval-1.54

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 9

64%

Researcher 3

21%

Professor / Associate Prof. 1

7%

Lecturer / Post doc 1

7%

Readers' Discipline

Tooltip

Computer Science 15

71%

Linguistics 4

19%

Neuroscience 1

5%

Social Sciences 1

5%

Save time finding and organizing research with Mendeley

Sign up for free