English

TourBERT: A pretrained language model for the tourism industry

Computation and Language 2022-05-20 v3 Artificial Intelligence Machine Learning

Abstract

The Bidirectional Encoder Representations from Transformers (BERT) is currently one of the most important and state-of-the-art models for natural language. However, it has also been shown that for domain-specific tasks it is helpful to pretrain BERT on a domain-specific corpus. In this paper, we present TourBERT, a pretrained language model for tourism. We describe how TourBERT was developed and evaluated. The evaluations show that TourBERT is outperforming BERT in all tourism-specific tasks.

Keywords

Cite

@article{arxiv.2201.07449,
  title  = {TourBERT: A pretrained language model for the tourism industry},
  author = {Veronika Arefieva and Roman Egger},
  journal= {arXiv preprint arXiv:2201.07449},
  year   = {2022}
}

Comments

Identified a mistake in our calculations. Will fix the problem within the next weeks and resubmit

R2 v1 2026-06-24T08:54:51.168Z