Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293466734> ?p ?o ?g. }
Showing items 1 to 69 of
69
with 100 items per page.
- W4293466734 abstract "Recurrent Neural Networks are showing much promise in many sub-areas of natural language processing, ranging from document classification to machine translation to automatic question answering. Despite their promise, many recurrent models have to read the whole text word by word, making it slow to handle long documents. For example, it is difficult to use a recurrent network to read a book and answer questions about it. In this paper, we present an approach of reading text while skipping irrelevant information if needed. The underlying model is a recurrent network that learns how far to jump after reading a few words of the input text. We employ a standard policy gradient method to train the model to make discrete jumping decisions. In our benchmarks on four different tasks, including number prediction, sentiment analysis, news article classification and automatic Q&A, our proposed model, a modified LSTM with jumping, is up to 6 times faster than the standard sequential LSTM, while maintaining the same or even better accuracy." @default.
- W4293466734 created "2022-08-29" @default.
- W4293466734 creator A5045729519 @default.
- W4293466734 creator A5081157085 @default.
- W4293466734 creator A5088551093 @default.
- W4293466734 date "2017-04-22" @default.
- W4293466734 modified "2023-09-27" @default.
- W4293466734 title "Learning to Skim Text" @default.
- W4293466734 doi "https://doi.org/10.48550/arxiv.1704.06877" @default.
- W4293466734 hasPublicationYear "2017" @default.
- W4293466734 type Work @default.
- W4293466734 citedByCount "0" @default.
- W4293466734 crossrefType "posted-content" @default.
- W4293466734 hasAuthorship W4293466734A5045729519 @default.
- W4293466734 hasAuthorship W4293466734A5081157085 @default.
- W4293466734 hasAuthorship W4293466734A5088551093 @default.
- W4293466734 hasBestOaLocation W42934667341 @default.
- W4293466734 hasConcept C104317684 @default.
- W4293466734 hasConcept C105580179 @default.
- W4293466734 hasConcept C119857082 @default.
- W4293466734 hasConcept C138885662 @default.
- W4293466734 hasConcept C147168706 @default.
- W4293466734 hasConcept C149364088 @default.
- W4293466734 hasConcept C154945302 @default.
- W4293466734 hasConcept C185592680 @default.
- W4293466734 hasConcept C203005215 @default.
- W4293466734 hasConcept C204321447 @default.
- W4293466734 hasConcept C41008148 @default.
- W4293466734 hasConcept C41895202 @default.
- W4293466734 hasConcept C44291984 @default.
- W4293466734 hasConcept C50644808 @default.
- W4293466734 hasConcept C554936623 @default.
- W4293466734 hasConcept C55493867 @default.
- W4293466734 hasConcept C66402592 @default.
- W4293466734 hasConcept C90805587 @default.
- W4293466734 hasConceptScore W4293466734C104317684 @default.
- W4293466734 hasConceptScore W4293466734C105580179 @default.
- W4293466734 hasConceptScore W4293466734C119857082 @default.
- W4293466734 hasConceptScore W4293466734C138885662 @default.
- W4293466734 hasConceptScore W4293466734C147168706 @default.
- W4293466734 hasConceptScore W4293466734C149364088 @default.
- W4293466734 hasConceptScore W4293466734C154945302 @default.
- W4293466734 hasConceptScore W4293466734C185592680 @default.
- W4293466734 hasConceptScore W4293466734C203005215 @default.
- W4293466734 hasConceptScore W4293466734C204321447 @default.
- W4293466734 hasConceptScore W4293466734C41008148 @default.
- W4293466734 hasConceptScore W4293466734C41895202 @default.
- W4293466734 hasConceptScore W4293466734C44291984 @default.
- W4293466734 hasConceptScore W4293466734C50644808 @default.
- W4293466734 hasConceptScore W4293466734C554936623 @default.
- W4293466734 hasConceptScore W4293466734C55493867 @default.
- W4293466734 hasConceptScore W4293466734C66402592 @default.
- W4293466734 hasConceptScore W4293466734C90805587 @default.
- W4293466734 hasLocation W42934667341 @default.
- W4293466734 hasOpenAccess W4293466734 @default.
- W4293466734 hasPrimaryLocation W42934667341 @default.
- W4293466734 hasRelatedWork W1980957807 @default.
- W4293466734 hasRelatedWork W2138247936 @default.
- W4293466734 hasRelatedWork W2251488256 @default.
- W4293466734 hasRelatedWork W2542068976 @default.
- W4293466734 hasRelatedWork W2578428189 @default.
- W4293466734 hasRelatedWork W2621423192 @default.
- W4293466734 hasRelatedWork W2747680751 @default.
- W4293466734 hasRelatedWork W3192794374 @default.
- W4293466734 hasRelatedWork W3198193297 @default.
- W4293466734 hasRelatedWork W4327531511 @default.
- W4293466734 isParatext "false" @default.
- W4293466734 isRetracted "false" @default.
- W4293466734 workType "article" @default.