Papers › Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition

Improved Differentiable Architecture Search for Language Modeling and Named Entity Recognition

1 Nov 2019IJCNLP 2019 11archive 2025-07-28

Yufan Jiang, Chi Hu, Tong Xiao, Chunliang Zhang, Jingbo Zhu

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.

PaperPDFCode

Code

jiangyingjunn/i-darts officialpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language ModelingLanguage ModellingNERNamed Entity RecognitionNamed Entity Recognition (NER)Neural Architecture Searchnamed-entity-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling PTB Diagnostic ECG Database I-DARTS PPL 56.0 #1 of 1 Archive leaderboard report
Named Entity Recognition (NER) CoNLL 2003 (English) I-DARTS + Flair F1 93.47 #21 of 73 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Differentiable NASLSTMSigmoid ActivationSoftmaxTanh Activation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections