Research map / Label-efficient and robust learning / Recognition and long-tail
SSMI: Semantic Similarity and Mutual Information Maximization Based Enhancement for Chinese NER
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 |
|---|---|---|---|
| select latent word boundaries using semantic similarity and add local and global mutual-information enhancement | BERT-based Chinese NER · OntoNote 4.0 | F1: 82.81 -> 83.52 | Helped |
| select latent word boundaries using semantic similarity and add local and global mutual-information enhancement | BERT-based Chinese NER · MSRA | F1: 95.42 -> 96.32 | Helped |
| select latent word boundaries using semantic similarity and add local and global mutual-information enhancement | BERT-based Chinese NER · Weibo | F1: 70.50 -> 72.83 | Helped |
| select latent word boundaries using semantic similarity and add local and global mutual-information enhancement | BERT-based Chinese NER · Resume | F1: 96.11 -> 97.33 | Helped |
| add semantic-similarity filtering of latent word boundaries (ablation) | SSMI · Ontonote 4.0 | F1: 79.19 -> 83.52 | Helped |
| add semantic-similarity filtering of latent word boundaries (ablation) | SSMI · MSRA | F1: 94.90 -> 96.32 | Helped |
| add semantic-similarity filtering of latent word boundaries (ablation) | SSMI · Weibo | F1: 68.55 -> 72.83 | Helped |
| add semantic-similarity filtering of latent word boundaries (ablation) | SSMI · Resume | F1: 95.07 -> 97.33 | Helped |
| add global mutual information maximization (ablation) | SSMI · Ontonote 4.0 | F1: 74.08 -> 83.52 | Helped |
| add global mutual information maximization (ablation) | SSMI · MSRA | F1: 92.53 -> 96.32 | Helped |
| add global mutual information maximization (ablation) | SSMI · Weibo | F1: 66.83 -> 72.83 | Helped |
| add global mutual information maximization (ablation) | SSMI · Resume | F1: 94.29 -> 97.33 | Helped |
Closest papers by meaning
- SENCR: A Span Enhanced Two-Stage Network with Counterfactual Rethinking for Chinese NER (AAAI 2024 · similarity 0.87)
- ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context (AAAI 2024 · similarity 0.85)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.85)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.85)
- Narrowing the Gap between Supervised and Unsupervised Sentence Representation Learning with Large Language Model (AAAI 2024 · similarity 0.84)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · 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.