Speed Reading: Learning to Read ForBackward via Shuttle

2018-10-01 · EMNLP 2018 10 · Tsu-Jui Fu, Wei-Yun Ma

We present LSTM-Shuttle, which applies human speed reading techniques to natural language processing tasks for accurate and efficient comprehension. In contrast to previous work, LSTM-Shuttle not only reads shuttling forward but also goes back. Shuttling forward enables high efficiency, and going backward gives the model a chance to recover lost information, ensuring better prediction. We evaluate LSTM-Shuttle on sentiment analysis, news classification, and cloze on IMDB, Rotten Tomatoes, AG, and Children{'}s Book Test datasets. We show that LSTM-Shuttle predicts both better and more quickly. To demonstrate how LSTM-Shuttle actually behaves, we also analyze the shuttling operation and present a case study.

📄 PDF Abstract BibTeX

Code (1)

tsujuifu/pytorch_lstm-shuttle 공식 구현 pytorch

Tasks

Document Classification Document Summarization General Classification Machine Translation Named Entity Recognition (NER)News Classification Part-Of-Speech Tagging Question Answering Reading Comprehension Sentiment Analysis

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Automated Estimation of Impact Time, Impact Location, and Shuttlecock Speed in Badminton Smashes Using Event Cameras

2026-05-27 · Yudai Washida, Yuto Kase, Kai Ishibe, Ryoma Yasuda 외 arxiv

Quantifying impact phenomena in badminton smashes is important for evaluating both athletic performance and equipment; however, conventional measurement systems involve trade-offs between temporal resolution, data effici…

Optimizing Odia Braille Literacy: The Influence of Speed on Error Reduction and Enhanced Comprehension

2023-10-12 · Monnie Parida, Manjira Sinha, Anupam Basu, Pabitra Mitra

This study aims to conduct an extensive detailed analysis of the Odia Braille reading comprehension among students with visual disability. Specifically, the study explores their reading speed and hand or finger movements…

Reading Comprehension

Neural Speed Reading Audited

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Anders S{\o}gaard

Several approaches to neural speed reading have been presented at major NLP and machine learning conferences in 2017{--}20; i.e., {``}human-inspired{''} recurrent network architectures that learn to {``}read{''} text fas…

Classification Document Classification

AdaptiFont: Increasing Individuals' Reading Speed with a Generative Font Model and Bayesian Optimization

2021-04-21 · Florian Kadner, Yannik Keller, Constantin A. Rothkopf

Digital text has become one of the primary ways of exchanging knowledge, but text needs to be rendered to a screen to be read. We present AdaptiFont, a human-in-the-loop system that is aimed at interactively increasing r…

Active Learning Bayesian Optimization Font Generation

Neural Speed Reading with Structural-Jump-LSTM

2019-03-20 · ICLR 2019 5 · Christian Hansen, Casper Hansen, Stephen Alstrup, Jakob Grue Simonsen 외

Recurrent neural networks (RNNs) can model natural language by sequentially 'reading' input tokens and outputting a distributed representation of each token. Due to the sequential nature of RNNs, inference time is linear…

Sentence