This paper investigates unsupervised methods for Named Entity Recognition (NER) when dealing with small or unlabeled datasets across multiple domains. It proposes using unsupervised pre-training to identify entities without annotations, followed by transfer learning on limited datasets. The research addresses challenges like domain variability and data sparsity by exploring techniques such as data augmentation, few-shot learning, and domain adversarial training to improve NER system performance and adaptability. AI
IMPACT This research could lead to more efficient and adaptable NLP applications in domains with limited annotated data.
RANK_REASON The cluster contains two identical arXiv preprints detailing a research paper on NLP methods.
Read on arXiv cs.NE (Neural & Evolutionary) →
- arXiv
- Domain-Adversarial Training for Session Independent EMG-based Speech Recognition
- Few-shot learning
- Hugging Face
- Multidomain Named Entity Recognition
- Named Entity Recognition
- natural language processing
- transfer learning
- alphaXiv
- CatalyzeX Code Finder for Papers
- Connected Papers
- CORE Recommender
- DagsHub
- data augmentation
- Gotit.pub
- Litmaps
- ScienceCast
- scite Smart Citations
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
