X-stance: A Multilingual Multi-Target Dataset for Stance Detection

Jannis Vamvas, Rico Sennrich

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We extract a large-scale stance detection dataset from comments written by candidates of elections in Switzerland. The dataset consists of German, French and Italian text, allowing for a cross-lingual evaluation of stance detection. It contains 67 000 comments on more than 150 political issues (targets). Unlike stance detection models that have specific target issues, we use the dataset to train a single model on all the issues. To make learning across targets possible, we prepend to each instance a natural question that represents the target (e.g. “Do you support X?”). Baseline results from multi-lingual BERT show that zero-shot cross-lingual and cross-target transfer of stance detection is moderately successful with this approach.
Original languageEnglish
Title of host publicationProceedings of the 5th Swiss Text Analytics Conference (SwissText) & 16th Conference on Natural Language Processing (KONVENS)
Number of pages12
Publication statusPublished - 23 Jun 2020
Event5th SwissText & 16th KONVENS Joint Conference 2020 - Virtual conference, Switzerland
Duration: 23 Jun 202025 Jun 2020

Publication series

NameCEUR Workshop Proceedings
ISSN (Electronic)1613-0073


Conference5th SwissText & 16th KONVENS Joint Conference 2020
Abbreviated titleSwissText and KONVENS 2020
CityVirtual conference
Internet address

Cite this