Social Media Variety Geolocation with geoBERT

Social Media Variety Geolocation with geoBERT
复制标题

使用 geoBERT 进行社交媒体多样性地理定位

DOI:
--
复制
发表时间:
2021
期刊:
Workshop on NLP for Similar Languages, Varieties and Dialects
影响因子:
--
通讯作者:
N. Ljubešić
N. Ljubešić
中科院分区:
--
文献类型:
--
作者:
Yves Scherrer;N. Ljubešić

文献摘要

被引文献

相似文献

本文介绍了赫尔辛基-卢布尔雅那对VarDial 2021社交媒体多样化地理定位共享任务的贡献。在成功参加VarDial 2020之后,我们再次提出了基于BERT架构的约束和无约束系统。在本文中,我们报告了不同标记化设置和不同预训练模型的实验,并将我们的无参数回归方法与VarDial 2020其他参与者提出的各种分类方案进行了对比。代码和性能最好的预训练模型都是免费提供的。
This paper describes the Helsinki–Ljubljana contribution to the VarDial 2021 shared task on social media variety geolocation. Following our successful participation at VarDial 2020, we again propose constrained and unconstrained systems based on the BERT architecture. In this paper, we report experiments with different tokenization settings and different pre-trained models, and we contrast our parameter-free regression approach with various classification schemes proposed by other participants at VarDial 2020. Both the code and the best-performing pre-trained models are made freely available.