Skim-Reading Task

A Skim-Reading Task is a Strategic Reading Task that allows to locate and comprehend main ideas within a text document ignoring specific details.

AKA: Speed-Reading Task.
Context:
- It can be solved by a Skim-Reading System that implements a Skim-Reading Algorithm.
- It can range from being a Human Skim-Reading Task to being Machine-Aided Skim Reading Task.
- It can be detected using a Skim-Reading Detection Task.
Example(s):
Counter-Example(s):
See: Reading-Skimming Classification Task, Natural Language Processing, Deep Learning, Knowledge Discovery, Named Entity Recognition, Sentiment Analysis, Bag-of-Words Vectorization Task.

References

(Wikipedia, 2019) ⇒ https://en.wikipedia.org/wiki/Speed_reading Retrieved:2019-12-17.
- Speed reading is any of several techniques used to improve one's ability to read quickly. Speed reading methods include chunking and minimizing subvocalization. The many available speed reading training programs include books, videos, software, and seminars. There is very little scientific evidence regarding speed reading.

(Seo et al., 2018) ⇒ Minjoon Seo, Sewon Min, Ali Farhadi, and Hannaneh Hajishirzi. (2018). “Neural Speed Reading via Skim-RNN.” In: International Conference on Learning Representations.
- QUOTE: Inspired by the principles of human's speed reading, we introduce Skim-RNN (Figure 1), which makes a fast decision on the significance of each input (to the downstream task) and ‘skims’ through unimportant input tokens by using a smaller RNN to update only a fraction of the hidden state. When the decision is to ‘fully read’, Skim-RNN updates the entire hidden state with the default RNN cell.
  
  Figure 1: The schematic of Skim-RNN on a sample sentence from Stanford Sentiment Treebank: “intelligent and invigorating film”. At time step 1, Skim-RNN makes the decision to read or skim $x_1$ by using Equation 1 on $h_0$ and $x_1$. Since ‘intelligent’ is an important word for sentiment, it decides to read (blue diamond) by obtaining a full-size hidden state with the big RNN and updating the entire previous hidden state. At time step 2, Skim-RNN decides to skim (empty diamond) the word ‘and’ by updating the first few dimensions of the hidden state using small RNN.

(Fu & Ma, 2018) ⇒ Tsu-Jui Fu, and Wei-Yun Ma. (2018). “Speed Reading: Learning to Read ForBackward via Shuttle.” In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.

(Johansen & Socher, 2017) ⇒ Alexander Johansen, and Richard Socher. (2017). “Learning When to Skim and When to Read.” In: Proceedings of the 2nd Workshop on Representation Learning for NLP.

(Yu et al., 2017) ⇒ Adams Wei Yu, Hongrae Lee, and Quoc Le. (2017). “Learning to Skim Text.” In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).