Matches in SemOpenAlex for { <https://semopenalex.org/work/W2890116189> ?p ?o ?g. }
- W2890116189 abstract "In sentence compression, the task of shortening sentences while retaining the original meaning, models tend to be trained on large corpora containing pairs of verbose and compressed sentences. To remove the need for paired corpora, we emulate a summarization task and add noise to extend sentences and train a denoising auto-encoder to recover the original, constructing an end-to-end training regime without the need for any examples of compressed sentences. We conduct a human evaluation of our model on a standard text summarization dataset and show that it performs comparably to a supervised baseline based on grammatical correctness and retention of meaning. Despite being exposed to no target data, our unsupervised models learn to generate imperfect but reasonably readable sentence summaries. Although we underperform supervised models based on ROUGE scores, our models are competitive with a supervised baseline based on human evaluation for grammatical correctness and retention of meaning." @default.
- W2890116189 created "2018-09-27" @default.
- W2890116189 creator A5024882131 @default.
- W2890116189 creator A5047763717 @default.
- W2890116189 date "2018-01-01" @default.
- W2890116189 modified "2023-10-12" @default.
- W2890116189 title "Unsupervised Sentence Compression using Denoising Auto-Encoders" @default.
- W2890116189 cites W1843891098 @default.
- W2890116189 cites W1964157370 @default.
- W2890116189 cites W1964326564 @default.
- W2890116189 cites W2025768430 @default.
- W2890116189 cites W2081265723 @default.
- W2890116189 cites W2083451366 @default.
- W2890116189 cites W2115167129 @default.
- W2890116189 cites W2118681326 @default.
- W2890116189 cites W2126725946 @default.
- W2890116189 cites W2133182690 @default.
- W2890116189 cites W2153982529 @default.
- W2890116189 cites W2154652894 @default.
- W2890116189 cites W2250539671 @default.
- W2890116189 cites W2250646737 @default.
- W2890116189 cites W2251654079 @default.
- W2890116189 cites W2293778248 @default.
- W2890116189 cites W2467173223 @default.
- W2890116189 cites W2526471240 @default.
- W2890116189 cites W2528130257 @default.
- W2890116189 cites W2574535369 @default.
- W2890116189 cites W2606974598 @default.
- W2890116189 cites W2612675303 @default.
- W2890116189 cites W2740132093 @default.
- W2890116189 cites W2799124508 @default.
- W2890116189 cites W2899771611 @default.
- W2890116189 cites W2951442567 @default.
- W2890116189 cites W2962768052 @default.
- W2890116189 cites W2962805889 @default.
- W2890116189 cites W2962824887 @default.
- W2890116189 cites W2963804993 @default.
- W2890116189 cites W2963929190 @default.
- W2890116189 cites W2964121744 @default.
- W2890116189 cites W2964266061 @default.
- W2890116189 cites W2964308564 @default.
- W2890116189 doi "https://doi.org/10.18653/v1/k18-1040" @default.
- W2890116189 hasPublicationYear "2018" @default.
- W2890116189 type Work @default.
- W2890116189 sameAs 2890116189 @default.
- W2890116189 citedByCount "18" @default.
- W2890116189 countsByYear W28901161892018 @default.
- W2890116189 countsByYear W28901161892019 @default.
- W2890116189 countsByYear W28901161892020 @default.
- W2890116189 countsByYear W28901161892021 @default.
- W2890116189 countsByYear W28901161892023 @default.
- W2890116189 crossrefType "proceedings-article" @default.
- W2890116189 hasAuthorship W2890116189A5024882131 @default.
- W2890116189 hasAuthorship W2890116189A5047763717 @default.
- W2890116189 hasBestOaLocation W28901161891 @default.
- W2890116189 hasConcept C111368507 @default.
- W2890116189 hasConcept C111919701 @default.
- W2890116189 hasConcept C11413529 @default.
- W2890116189 hasConcept C115961682 @default.
- W2890116189 hasConcept C118505674 @default.
- W2890116189 hasConcept C12725497 @default.
- W2890116189 hasConcept C127313418 @default.
- W2890116189 hasConcept C154945302 @default.
- W2890116189 hasConcept C162324750 @default.
- W2890116189 hasConcept C170858558 @default.
- W2890116189 hasConcept C187736073 @default.
- W2890116189 hasConcept C204321447 @default.
- W2890116189 hasConcept C2777530160 @default.
- W2890116189 hasConcept C2780451532 @default.
- W2890116189 hasConcept C28490314 @default.
- W2890116189 hasConcept C41008148 @default.
- W2890116189 hasConcept C55439883 @default.
- W2890116189 hasConcept C99498987 @default.
- W2890116189 hasConceptScore W2890116189C111368507 @default.
- W2890116189 hasConceptScore W2890116189C111919701 @default.
- W2890116189 hasConceptScore W2890116189C11413529 @default.
- W2890116189 hasConceptScore W2890116189C115961682 @default.
- W2890116189 hasConceptScore W2890116189C118505674 @default.
- W2890116189 hasConceptScore W2890116189C12725497 @default.
- W2890116189 hasConceptScore W2890116189C127313418 @default.
- W2890116189 hasConceptScore W2890116189C154945302 @default.
- W2890116189 hasConceptScore W2890116189C162324750 @default.
- W2890116189 hasConceptScore W2890116189C170858558 @default.
- W2890116189 hasConceptScore W2890116189C187736073 @default.
- W2890116189 hasConceptScore W2890116189C204321447 @default.
- W2890116189 hasConceptScore W2890116189C2777530160 @default.
- W2890116189 hasConceptScore W2890116189C2780451532 @default.
- W2890116189 hasConceptScore W2890116189C28490314 @default.
- W2890116189 hasConceptScore W2890116189C41008148 @default.
- W2890116189 hasConceptScore W2890116189C55439883 @default.
- W2890116189 hasConceptScore W2890116189C99498987 @default.
- W2890116189 hasLocation W28901161891 @default.
- W2890116189 hasLocation W28901161892 @default.
- W2890116189 hasOpenAccess W2890116189 @default.
- W2890116189 hasPrimaryLocation W28901161891 @default.
- W2890116189 hasRelatedWork W1517743118 @default.
- W2890116189 hasRelatedWork W2008129036 @default.
- W2890116189 hasRelatedWork W2104752822 @default.
- W2890116189 hasRelatedWork W2330186386 @default.
- W2890116189 hasRelatedWork W2347941600 @default.