Research map / Graph learning / Knowledge and temporal graphs
Zero-Shot Cross-Lingual Machine Reading Comprehension via Inter-sentence Dependency Graph
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 |
|---|---|---|---|
| Add the ISDG encoder to XLM-R | XLM-R · XQuAD avg | F1: 81.4 -> 82.4 | Helped |
| Add the ISDG encoder to XLM-R | XLM-R · MLQA avg | F1: 75.3 -> 75.6 | Helped |
| Add the ISDG encoder to mT5 | mT5 · TyDiQA-GoldP avg | F1: 68.4 -> 72.2 | Helped |
| Add the ISDG encoder to mT5 | mT5 · TyDiQA-GoldP avg | EM: 52.8 -> 58.0 | Helped |
| Add the ISDG encoder to mT5 | mT5 · TyDiQA-GoldP Korean | F1: 60.8 -> 66.0; 57.3 -> 52.5 | Mixed |
| Add local one-hop graph encoding to POS-only features (ablation) | mBERT + POS · XQuAD German | F1: +1.2 | Helped |
| Add local and global graph encoding to POS-only features (ablation) | mBERT + POS · XQuAD German | F1: +2.3 | Helped |
| Add local one-hop graph encoding to POS-only features (ablation) | XLM-R + POS · XQuAD German | F1: +0.5 | Helped |
| Add local and global graph encoding to POS-only features (ablation) | XLM-R + POS · XQuAD German | F1: +0.8 | Helped |
| Add local one-hop graph encoding to POS-only features (ablation) | mT5 + POS · XQuAD German | F1: +0.8 | Helped |
| Add local and global graph encoding to POS-only features (ablation) | mT5 + POS · XQuAD German | F1: +1.5 | Helped |
Closest papers by meaning
- A Graph Fusion Approach for Cross-Lingual Machine Reading Comprehension (AAAI 2023 · similarity 0.92)
- From Good to Best: Two-Stage Training for Cross-Lingual Machine Reading Comprehension (AAAI 2022 · similarity 0.89)
- Unsupervised Interlingual Semantic Representations from Sentence Embeddings for Zero-Shot Cross-Lingual Transfer (AAAI 2020 · similarity 0.87)
- Dynamic Syntactic Feature Filtering and Injecting Networks for Cross-lingual Dependency Parsing (AAAI 2025 · similarity 0.86)
- MCIF: Multimodal Crosslingual Instruction-Following Benchmark from Scientific Talks (ICLR 2026 · similarity 0.85)
- XCOT: Cross-lingual Instruction Tuning for Cross-lingual Chain-of-Thought Reasoning (AAAI 2025 · similarity 0.84)
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.