Research map / Label-efficient and robust learning / Recognition and long-tail
Dynamic Modeling Cross- and Self-Lattice Attention Network 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 |
|---|---|---|---|
| use DCSAN instead of FLAT+BERT | Chinese NER models · Resume | F1: +0.81% | Helped |
| use DCSAN instead of FLAT+BERT | Chinese NER models · MSRA | F1: +0.32% | Helped |
| use DCSAN instead of FLAT+BERT | Chinese NER models · Weibo | F1: +2.72% | Helped |
| use DCSAN instead of Multi-Digraph | Chinese NER models · E-commerce | F1: 7.42% F1 | Helped |
| add cross-lattice attention (ablation) | DCSAN · E-commerce | F1: 1.66 | Helped |
| use gated fusion instead of simple feature addition (ablation) | DCSAN · E-commerce | F1: -1.40% | Helped |
| add self-lattice attention (ablation) | DCSAN · E-commerce | F1: 1.13% | Helped |
| add both attention modules (ablation) | DCSAN · E-commerce | F1: -5.13% | Helped |
| use BERT embeddings instead of pretrained character embeddings (ablation) | DCSAN · E-commerce | F1: -2.53% | Helped |
Closest papers by meaning
- LADA-Trans-NER: Adaptive Efficient Transformer for Chinese Named Entity Recognition Using Lexicon-Attention and Data-Augmentation (AAAI 2023 · similarity 0.88)
- SENCR: A Span Enhanced Two-Stage Network with Counterfactual Rethinking for Chinese NER (AAAI 2024 · similarity 0.88)
- Three Heads Are Better than One: Improving Cross-Domain NER with Progressive Decomposed Network (AAAI 2024 · similarity 0.85)
- ConsistNER: Towards Instructive NER Demonstrations for LLMs with the Consistency of Ontology and Context (AAAI 2024 · similarity 0.84)
- PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition (NeurIPS 2024 · similarity 0.84)
- MCL-NER: Cross-Lingual Named Entity Recognition via Multi-View Contrastive Learning (AAAI 2024 · similarity 0.83)
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.