TempoFormer: A Transformer for Temporally-aware Representations in Change Detection

Talia Tseriotou, Adam Tsakalidis, Maria Liakata


Abstract
Dynamic representation learning plays a pivotal role in understanding the evolution of linguistic content over time. On this front both context and time dynamics as well as their interplay are of prime importance. Current approaches model context via pre-trained representations, which are typically temporally agnostic. Previous work on modelling context and temporal dynamics has used recurrent methods, which are slow and prone to overfitting. Here we introduce TempoFormer, the first task-agnostic transformer-based and temporally-aware model for dynamic representation learning. Our approach is jointly trained on inter and intra context dynamics and introduces a novel temporal variation of rotary positional embeddings. The architecture is flexible and can be used as the temporal representation foundation of other models or applied to different transformer-based architectures. We show new SOTA performance on three different real-time change detection tasks.
Anthology ID:
2024.emnlp-main.1095
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
19635–19653
Language:
URL:
https://aclanthology.org/2024.emnlp-main.1095
DOI:
10.18653/v1/2024.emnlp-main.1095
Bibkey:
Cite (ACL):
Talia Tseriotou, Adam Tsakalidis, and Maria Liakata. 2024. TempoFormer: A Transformer for Temporally-aware Representations in Change Detection. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 19635–19653, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
TempoFormer: A Transformer for Temporally-aware Representations in Change Detection (Tseriotou et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.1095.pdf