Adversarial Active Learning for Sequences Labeling and Generation
| Autor: | Yilin Shen, Hongxia Jin, Yue Deng, Chen Kawai |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Adversarial system
Computer science Active learning (machine learning) business.industry 020204 information systems 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing 02 engineering and technology Artificial intelligence business |
| Zdroj: | IJCAI |
| DOI: | 10.24963/ijcai.2018/558 |
| Popis: | We introduce an active learning framework for general sequence learning tasks including sequence labeling and generation. Most existing active learning algorithms mainly rely on an uncertainty measure derived from the probabilistic classifier for query sample selection. However, such approaches suffer from two shortcomings in the context of sequence learning including 1) cold start problem and 2) label sampling dilemma. To overcome these shortcomings, we propose a deep-learning-based active learning framework to directly identify query samples from the perspective of adversarial learning. Our approach intends to offer labeling priorities for sequences whose information content are least covered by existing labeled data. We verify our sequence-based active learning approach on two tasks including sequence labeling and sequence generation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|