Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training
Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Standard
Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training. / Hardalov, Momchil; Arora, Arnav; Nakov, Preslav; Augenstein, Isabelle.
I: Proceedings of the International Joint Conference on Artificial Intelligence, Bind 36, Nr. 10, 2022, s. 10729-10737.Publikation: Bidrag til tidsskrift › Konferenceartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-Training
AU - Hardalov, Momchil
AU - Arora, Arnav
AU - Nakov, Preslav
AU - Augenstein, Isabelle
PY - 2022
Y1 - 2022
N2 - The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts are often expressed in many different languages depending on the user and the platform, which can be a local news outlet, a social media platform, a news forum, etc. Most research in stance detection, however, has been limited to working with a single language and on a few limited targets, with little work on cross-lingual stance detection. Moreover, non-English sources of labelled data are often scarce and present additional challenges. Recently, large multilingual language models have substantially improved the performance on many non-English tasks, especially such with limited numbers of examples. This highlights the importance of model pre-training and its ability to learn from few examples. In this paper, we present the most comprehensive study of cross-lingual stance detection to date: we experiment with 15 diverse datasets in 12 languages from 6 language families, and with 6 low-resource evaluation settings each. For our experiments, we build on pattern-exploiting training, proposing the addition of a novel label encoder to simplify the verbalisation procedure. We further propose sentiment-based generation of stance data for pre-training, which shows sizeable improvement of more than 6% F1 absolute in low-shot settings compared to several strong baselines.
AB - The goal of stance detection is to determine the viewpoint expressed in a piece of text towards a target. These viewpoints or contexts are often expressed in many different languages depending on the user and the platform, which can be a local news outlet, a social media platform, a news forum, etc. Most research in stance detection, however, has been limited to working with a single language and on a few limited targets, with little work on cross-lingual stance detection. Moreover, non-English sources of labelled data are often scarce and present additional challenges. Recently, large multilingual language models have substantially improved the performance on many non-English tasks, especially such with limited numbers of examples. This highlights the importance of model pre-training and its ability to learn from few examples. In this paper, we present the most comprehensive study of cross-lingual stance detection to date: we experiment with 15 diverse datasets in 12 languages from 6 language families, and with 6 low-resource evaluation settings each. For our experiments, we build on pattern-exploiting training, proposing the addition of a novel label encoder to simplify the verbalisation procedure. We further propose sentiment-based generation of stance data for pre-training, which shows sizeable improvement of more than 6% F1 absolute in low-shot settings compared to several strong baselines.
U2 - 10.1609/aaai.v36i10.21318
DO - 10.1609/aaai.v36i10.21318
M3 - Conference article
VL - 36
SP - 10729-10737.
JO - Proceedings of the International Joint Conference on Artificial Intelligence
JF - Proceedings of the International Joint Conference on Artificial Intelligence
SN - 1045-0823
IS - 10
T2 - 36th AAAI Conference on Artificial Intelligence (AAAI-22)
Y2 - 28 February 2022 through 1 March 2022
ER -
ID: 339340380