Cross-Domain Label-Adaptive Stance Detection
Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Standard
Cross-Domain Label-Adaptive Stance Detection. / Hardalov, Momchil; Arora, Arnav; Nakov, Preslav; Augenstein, Isabelle.
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2021. s. 9011-9028.Publikation: Bidrag til bog/antologi/rapport › Konferencebidrag i proceedings › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Cross-Domain Label-Adaptive Stance Detection
AU - Hardalov, Momchil
AU - Arora, Arnav
AU - Nakov, Preslav
AU - Augenstein, Isabelle
PY - 2021
Y1 - 2021
N2 - Stance detection concerns the classification of a writer’s viewpoint towards a target. There are different task variants, e.g., stance of a tweet vs. a full article, or stance with respect to a claim vs. an (implicit) topic. Moreover, task definitions vary, which includes the label inventory, the data collection, and the annotation protocol. All these aspects hinder cross-domain studies, as they require changes to standard domain adaptation approaches. In this paper, we perform an in-depth analysis of 16 stance detection datasets, and we explore the possibility for cross-domain learning from them. Moreover, we propose an end-to-end unsupervised framework for out-of-domain prediction of unseen, user-defined labels. In particular, we combine domain adaptation techniques such as mixture of experts and domain-adversarial training with label embeddings, and we demonstrate sizable performance gains over strong baselines, both (i) in-domain, i.e., for seen targets, and (ii) out-of-domain, i.e., for unseen targets. Finally, we perform an exhaustive analysis of the cross-domain results, and we highlight the important factors influencing the model performance.
AB - Stance detection concerns the classification of a writer’s viewpoint towards a target. There are different task variants, e.g., stance of a tweet vs. a full article, or stance with respect to a claim vs. an (implicit) topic. Moreover, task definitions vary, which includes the label inventory, the data collection, and the annotation protocol. All these aspects hinder cross-domain studies, as they require changes to standard domain adaptation approaches. In this paper, we perform an in-depth analysis of 16 stance detection datasets, and we explore the possibility for cross-domain learning from them. Moreover, we propose an end-to-end unsupervised framework for out-of-domain prediction of unseen, user-defined labels. In particular, we combine domain adaptation techniques such as mixture of experts and domain-adversarial training with label embeddings, and we demonstrate sizable performance gains over strong baselines, both (i) in-domain, i.e., for seen targets, and (ii) out-of-domain, i.e., for unseen targets. Finally, we perform an exhaustive analysis of the cross-domain results, and we highlight the important factors influencing the model performance.
U2 - 10.18653/v1/2021.emnlp-main.710
DO - 10.18653/v1/2021.emnlp-main.710
M3 - Article in proceedings
SP - 9011
EP - 9028
BT - Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
PB - Association for Computational Linguistics
T2 - 2021 Conference on Empirical Methods in Natural Language Processing
Y2 - 1 November 2021 through 1 November 2021
ER -
ID: 299691261