EMNLP Findings2024
An LLM-Enabled Knowledge Elicitation and Retrieval Framework for Zero-Shot Cross-Lingual Stance Identification
Ruike Zhang, Yuan Tian, Penghui Wei, Daniel Zeng, Wenji Mao
Abstract
Stance detection aims to identify the attitudes toward specific targets from text, which is an important research area in text mining and social media analytics. Existing research is mainly conducted in monolingual setting on English datasets. To tackle the data scarcity problem in low-resource languages, cross-lingual stance detection (CLSD) transfers the knowledge from high-resource (source) language to low-resource (target) language. The CLSD task is the most challenging in zero-shot setting when no training data is available in target language, and transferring stance-relevant knowledge learned from high-resource language to bridge the language gap is the key for improving the performance of zero-shot CLSD. In this paper, we leverage the capability of large language model (LLM) for stance knowledge acquisition, and propose KEAR, a knowledge elicitation and retrieval framework. The knowledge elicitation module in KEAR first derives different types of stance knowledge from LLM's reasoning process. Then, the knowledge retrieval module in KEAR matches the target language input to the most relevant stance knowledge for enhancing text representations. Experiments on multilingual datasets show the effectiveness of KEAR compared with competitive baselines as well as the CLSD approaches trained with labeled data in target language 1 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
2 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph cites Enhancing Cross-target Stance Detection with Transferable Semantic-Emotion Knowledge
- JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection cites Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge Graph
- JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance Detection cites Enhancing Cross-target Stance Detection with Transferable Semantic-Emotion Knowledge
Cited by top-tier papers2
Builds on11
- Unsupervised Cross-lingual Representation Learning at ScaleAlexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary et al.ACL 2020 · 539 citations
- Dense Passage Retrieval for Open-Domain Question AnsweringVladimir Karpukhin, Barlas Oguz, Sewon Min, Patrick Lewis et al.EMNLP 2020 · 142 citations
- JointCL: A Joint Contrastive Learning Framework for Zero-Shot Stance DetectionBin Liang, Qinglin Zhu, Xiang Li, Min Yang et al.ACL 2022 · 117 citations
- Enhancing Cross-target Stance Detection with Transferable Semantic-Emotion KnowledgeBowen Zhang, Min Yang, Xutao Li, Yunming Ye et al.ACL 2020 · 115 citations
- Enhancing Zero-shot and Few-shot Stance Detection with Commonsense Knowledge GraphRui Liu, Zheng Lin, Yutong Tan, Weiping WangACL Findings 2021 · 97 citations
Related papers
- Cross-Lingual Cross-Target Stance Detection with Dual Knowledge Distillation FrameworkRuike Zhang, Hanxuan Yang, Wenji MaoEMNLP 2023 · 5 citations
- Target-Oriented Relation Alignment for Cross-Lingual Stance DetectionRuike Zhang, Nan Xu, Hanxuan Yang, Yuan Tian et al.ACL Findings 2023 · 5 citations
- Few-Shot Cross-Lingual Stance Detection with Sentiment-Based Pre-trainingMomchil Hardalov, Arnav Arora, Preslav Nakov, Isabelle AugensteinAAAI 2022 · 72 citations
- Bilingual Zero-Shot Stance DetectionChenye Zhao, Cornelia CarageaACL 2025 · 1 citation
- A Reinforcement Learning Framework for Cross-Lingual Stance Detection Using Chain-of-Thought AlignmentBinghui Li, Minghui Zou, Xiaowang Zhang, Shizhan Chen et al.ACL Findings 2025 · 2 citations
