AI Paper Atlas

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

Robsut Wrod Reocginiton via Semi-Character Recurrent Neural Network

Keisuke Sakaguchi, Kevin Duh, Matt Post, Benjamin Van Durme

AAAI 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 97 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 semi-character inputs that preserve first and last characters and bag internal charactersscRNN · Penn Treebank test, jumbleaccuracy (%): 57.15 -> 98.96Improved
use semi-character inputs that preserve first and last characters and bag internal charactersscRNN · Penn Treebank test, deleteaccuracy (%): 37.01 -> 85.74Improved
use semi-character inputs that preserve first and last characters and bag internal charactersscRNN · Penn Treebank test, insertaccuracy (%): 88.54 -> 96.70Improved
increase BPTT from β=1 to β=3 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.69 -> 98.96No clear effect
increase BPTT from β=3 to β=5 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 98.91No clear effect
increase BPTT from β=3 to β=10 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 98.95No clear effect
reduce LSTM hidden units to 50 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 98.48No clear effect
reduce LSTM hidden units to 40 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 96.90Hurt
reduce LSTM hidden units to 30 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 94.15Hurt
reduce LSTM hidden units to 20 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 84.82Hurt
reduce LSTM hidden units to 15 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 73.32Hurt
reduce LSTM hidden units to 10 (ablation)scRNN · Penn Treebank test, jumbled wordsaccuracy (%): 98.96 -> 48.43Hurt

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