2019
EMNLP
EMNLP 2019
Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition
Abstract
AbstractIn this paper, we study differentiable neural architecture search (NAS) methods for natural language processing. In particular, we improve differentiable architecture search by removing the softmax-local constraint. Also, we apply differentiable NAS to named entity recognition (NER). It is the first time that differentiable NAS methods are adopted in NLP tasks other than language modeling. On both the PTB language modeling and CoNLL-2003 English NER data, our method outperforms strong baselines. It achieves a new state-of-the-art on the NER task.
🌉
Interdisciplinary Bridge
— Artificial Intelligence and Deep Learning and Machine Learning and Natural Language Processing
🧭
Keyword Pioneer
— differentiable architecture search
🐣
Hot Topic Early Bird
— model optimization
🐝
Cross-Pollinator
— Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Security & Privacy, Speech & Audio
Authors
Topics
Artificial Intelligence > Core AI > Model Compression
Machine Learning > Optimization & Theory > Neural Network Optimization
Deep Learning > Techniques > Model Architecture
Natural Language Processing > Understanding > Named Entity Recognition
Natural Language Processing > Generation > Language Modeling
Natural Language Processing > Applications > Named Entity Recognition
Deep Learning > Optimization & Theory > Optimization
Machine Learning > Learning Types > Neural Architecture Search