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 -