Research map / Architectures and efficiency / Neural architecture search
TextNAS: A Neural Architecture Search Space Tailored for Text Representation
Yujing Wang, Yaming Yang, Yiren Chen, Jing Bai, Ce Zhang, Guinan Su, Xiaoyu Kou, Yunhai Tong, Mao Yang, Lidong Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use the TextNAS text-tailored search space and transfer its discovered architecture | TextNAS · SST | accuracy: 52.10 -> 52.51 | Improved |
| Use the TextNAS text-tailored search space and transfer its discovered architecture | TextNAS · SST-B | accuracy: 88.90 -> 90.33 | Improved |
| Use TextNAS instead of the strongest listed baseline | TextNAS · Sogou | accuracy: 97.24 -> 96.76 | Hurt |
| Use TextNAS instead of the strongest listed baseline | TextNAS · Yelp | accuracy: 65.26 -> 66.56 | Improved |
| Use TextNAS instead of the strongest listed baseline | TextNAS · SNLI | accuracy: 86.7 -> 87.4 | Improved |
| Use a macro search space instead of a micro search space | ENAS search on text classification · SST | accuracy: 47.00 -> 51.55 | Improved |
| Use a macro search space instead of a micro search space | ENAS search on text classification · YAHOO | accuracy: 70.63 -> 73.16 | Improved |
| Use a macro search space instead of a micro search space | ENAS search on text classification · AMZ | accuracy: 58.27 -> 62.64 | Improved |
| Use a macro search space instead of a micro search space | ENAS search on text classification · CIFAR10 | accuracy: 97.11 -> 95.67 | Hurt |
Later papers that compared with this method
1 later accepted paper reports TEXTNAS as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- AutoAttend: Automated Attention Representation Search (ICML 2021 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- einspace: Searching for Neural Architectures from Fundamental Operations (NeurIPS 2024 · similarity 0.89)
- Searching a High Performance Feature Extractor for Text Recognition Network (TPAMI 2022 · similarity 0.89)
- Active Discriminative Text Representation Learning (AAAI 2017 · similarity 0.88)
- Insights from the Use of Previously Unseen Neural Architecture Search Datasets (CVPR 2024 · similarity 0.87)
- Encodings for Prediction-based Neural Architecture Search (ICML 2024 · similarity 0.86)
- Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe (NeurIPS 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
