Fast and Accurate Text Classification: Skimming, Rereading and Early Stopping

By Keyi Yu, Yang Liu, Alexander Gerhard Schwing, Jian Peng. 2018

26 citations recorded by the source corpus.

Subfields: Information Extraction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Extraction

1. Wei-Yun Ma
2. Tsu-Jui Fu

Citations in the corpus

• A Survey on Dynamic Neural Networks for Natural Language Processing (2022, background): “Yu et al. (2018) add a re-reading operation to LSTM-Jump (Yu et al., 2017) which allows the model to stay on the current time step, allocating more computation to important information.”
• Speed Reading: Learning to Read ForBackward via Shuttle (2018, methodology): “From another perspective, (Yu et al., 2018) attempt to model early stopping behavior, deciding whether the model can answer confidently based on the hidden states.”
• Neural Speed Reading with Structural-Jump-LSTM (2019, unknown): “This combined approach of both skipping and jumping according to text structure yields notable gains in efficiency (reduced FLOPs) without loss of effectiveness (accuracy).”
• Skipping RNN State Updates without Retraining the Original Model (2019, methodology): “There have been multiple works on skipping RNN state updates [1, 4, 11, 17, 18].”