EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction

Wei Sun, Tingyu Qu, Jesse Davis, Marie-Francine Moens

Transactions of the Association for Computational Linguistics · 13.10.2026 · 14 · 2603-2624

DOI: 10.1162/tacl.a.817 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 13.10.2026. Verfasst von Wei Sun und 3 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Temporal relation extraction determines whether an event occurs before, after, or simultaneously with another event. Therefore, it relies on accurately modeling how the two events interact. Mainstream systems achieve this by concatenating event spans or using shallow fusion, which works well when all model parameters are trainable. However, in parameter-efficient fine-tuning, low-rank bottlenecks restrict information flow and prevent these interaction signals from passing through, leading to clear performance drops. To address this limitation, we propose a theoretically grounded architecture, Convolutional Bottleneck Interaction (CBI), which first applies lightweight depthwise convolution to enhance event representations and then uses element-wise multiplication to capture effective event-event interactions inside the bottleneck. Across five datasets and seven backbone models in the Adapter and LoRA settings, CBI provides consistent and substantial gains, up to +31.7 micro F1, while adding minimal computational cost, showing that explicit interaction inside low-rank spaces is crucial for temporal relation extraction. The code is available at https://github.com/VRCMF/CIF.git.

Zitieren

APA

Sun, W., Qu, T., Davis, J., & Moens, M. (2026). Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction. Transactions of the Association for Computational Linguistics, 14, 2603-2624. https://doi.org/10.1162/tacl.a.817

Vancouver

Sun W, Qu T, Davis J, Moens M. Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction. Transactions of the Association for Computational Linguistics. 2026;14:2603-2624. doi:10.1162/tacl.a.817

BibTeX
@article{Sun2026,
  author = {Sun, Wei and Qu, Tingyu and Davis, Jesse and Moens, Marie-Francine},
  title = {Event Interaction in Low-Rank Bottlenecks for Temporal Relation Extraction},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2026},
  volume = {14},
  pages = {2603--2624},
  doi = {10.1162/tacl.a.817}
}
Kostenlos starten →