AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Learning Multi-Level Dependencies for Robust Word Recognition

Zhiwei Wang, Hui Liu, Jiliang Tang, Songfan Yang, Gale Yan Huang, Zitao Liu

AAAI 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 7 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use MUDE's character-level encoder and word-level contextual model instead of scRNNWord recognition · PER, DEL, INS, SUBaccuracy (%): 98.23 -> 98.81; 91.55 -> 95.86; 95.95 -> 97.16; 87.09 -> 90.52Improved
Use MUDE's character-level encoder and word-level contextual model instead of scRNNWord recognition · W-PER, W-DEL, W-INS, W-SUBaccuracy (%): 97.36 -> 98.75; 89.99 -> 93.29; 95.96 -> 97.10; 81.12 -> 85.17Improved
Add character-level sequence-to-sequence training (beta 1 rather than beta 0) (ablation)MUDE · W-PERprediction lossImproved
Add character-level sequence-to-sequence training (beta 1 rather than beta 0) (ablation)MUDE · W-PERsequence-to-sequence lossImproved
Train with W-ALL noise augmentationMUDE · Deletion and substitution noise, including whole-word variantsaccuracy (%)Improved
Train with W-ALL noise augmentationMUDE · Permutation and insertion noiseaccuracy (%)Hurt
Train on one noise type and test on a different, dissimilar typeMUDE · Penn Treebank noise generalizationaccuracy (%)Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy