Research map / Vision-language and multimodal / CLIP and zero-shot
Neural Cross-Lingual Entity Linking
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 context LSTMs to the base similarity features (ablation) | Neural cross-lingual entity linker · CoNLL 2003 test-b | In-KB accuracy: 92.1 -> 93.0 | Helped |
| add LDC to the context-LSTM model (ablation) | Neural cross-lingual entity linker · CoNLL 2003 test-b | In-KB accuracy: 93.0 -> 93.4 | Helped |
| add MPCM to the context-LSTM and LDC model (ablation) | Neural cross-lingual entity linker · CoNLL 2003 test-b | In-KB accuracy: 93.4 -> 94.0 | Helped |
| add context LSTMs to the base similarity features (ablation) | Neural cross-lingual entity linker · TAC 2010 | In-KB accuracy: 85.0 -> 86.3 | Helped |
| add LDC to the context-LSTM model (ablation) | Neural cross-lingual entity linker · TAC 2010 | In-KB accuracy: 86.3 -> 86.9 | Helped |
| add MPCM to the context-LSTM and LDC model (ablation) | Neural cross-lingual entity linker · TAC 2010 | In-KB accuracy: 86.9 -> 87.4 | Helped |
| use Multi-CCA instead of LS embeddings (ablation) | Neural cross-lingual entity linker · TAC 2015 Spanish | Linking accuracy: 81.9 -> 82.3 | Helped |
| use Multi-CCA instead of CCA embeddings (ablation) | Neural cross-lingual entity linker · TAC 2015 Spanish | Linking accuracy: 81.8 -> 82.3 | Helped |
| use Multi-CCA instead of LS embeddings (ablation) | Neural cross-lingual entity linker · TAC 2015 Chinese | Linking accuracy: 84.1 -> 84.4 | Helped |
| use Multi-CCA instead of CCA embeddings (ablation) | Neural cross-lingual entity linker · TAC 2015 Chinese | Linking accuracy: 84.3 -> 84.4 | Helped |
Closest papers by meaning
- Zero-Shot Neural Transfer for Cross-Lingual Entity Linking (AAAI 2019 · similarity 0.90)
- Cross-Lingual Entity Linking for Web Tables (AAAI 2018 · similarity 0.89)
- Fine-Grained Entity Typing for Domain Independent Entity Linking (AAAI 2020 · similarity 0.88)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.86)
- A Dual-Way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking (AAAI 2024 · similarity 0.86)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.85)
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.