Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition
By Yufan Jiang, Chi Hu, Tong Xiao, Chunliang Zhang, Jingbo Zhu. 2019
83 citations recorded by the source corpus.
In 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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Xiaojun Chang
- Po-Yao (Bernie) Huang
- Shirui Pan
- Miao Zhang
- Steven W. Su
- Zhihui Li
- Reza Haffari
- Aixin Sun
Citations in the corpus
- A Comprehensive Survey of Neural Architecture Search (2020, methodology): “Comparison of cell structure of DARTS [17] and I-DARTS [79] in recurrent neural network.”
- iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients (2021, background): “…process of neural network design, with achieving remarkable success on image recognition (Tan & Le, 2019; Li et al., 2021b; 2020), language modeling (Jiang et al., 2019), and other deep learning ap-1 plications (Ren et al., 2020; Cheng et al., 2020; Chen et al., 2019b; Hu et al., 2021; Zhu et al.,…”
- A Survey on Deep Learning for Named Entity Recognition (2018, background): “5% [136] GloVe Plooled contextual embeddings RNN CRF CoNLL03: 93.”