Research map / Vision-language and multimodal / CLIP and zero-shot
Zero-Shot Cross-Lingual Event Argument Extraction with Language-Oriented Prefix-Tuning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use LAPIN instead of X-GEAR (mT5-large) | zero-shot cross-lingual EAE · ACE-2005 | average F1-score: +4.8% | Helped |
| Use LAPIN instead of X-GEAR (mT5-large) | zero-shot cross-lingual EAE · ERE | average F1-score: +2.3% | Helped |
| Add language-oriented prefix-tuning (ablation) | LAPIN (mT5-base) · ACE-2005 average all settings | F1-score: 48.8 (↓2.3) -> 51.1 | Helped |
| Select prefix tokens by breadth-first search from the trigger rather than sequentially (ablation) | LAPIN · ACE-2005 average all settings | F1-score: 50.0 (↓1.1) -> 51.1 (mT5-base); 55.0 (↓1.1) -> 56.1 (mT5-large) | Helped |
| Add the copy mechanism (ablation) | LAPIN · ACE-2005 average en/ar/zh⇒xx | F1-score: 49.7 (↓1.4) -> 51.1 (mT5-base); 54.1 (↓2.0) -> 56.1 (mT5-large) | Helped |
| Use trigger-centric dependency prefixes | LAPIN (mT5-base) · ACE-2005 argument distance distributions | F1-score | Mixed |
Closest papers by meaning
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · similarity 0.83)
- A Joint Framework with Heterogeneous-Relation-Aware Graph and Multi-Channel Label Enhancing Strategy for Event Causality Extraction (AAAI 2024 · similarity 0.82)
- Enhancing Multilingual LLM Pretraining with Model-Based Data Selection (NeurIPS 2025 · similarity 0.82)
- SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset (NeurIPS 2025 · similarity 0.82)
- GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction (ICLR 2024 · similarity 0.82)
- E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding (NeurIPS 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.