Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950470367> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W2950470367 abstract "Context plays an important role in human language understanding, thus it may also be useful for machines learning vector representations of language. In this paper, we explore an asymmetric encoder-decoder structure for unsupervised context-based sentence representation learning. We carefully designed experiments to show that neither an autoregressive decoder nor an RNN decoder is required. After that, we designed a model which still keeps an RNN as the encoder, while using a non-autoregressive convolutional decoder. We further combine a suite of effective designs to significantly improve model efficiency while also achieving better performance. Our model is trained on two different large unlabelled corpora, and in both cases the transferability is evaluated on a set of downstream NLP tasks. We empirically show that our model is simple and fast while producing rich sentence representations that excel in downstream tasks." @default.
- W2950470367 created "2019-06-27" @default.
- W2950470367 creator A5051364953 @default.
- W2950470367 creator A5063499488 @default.
- W2950470367 creator A5068625652 @default.
- W2950470367 creator A5071129405 @default.
- W2950470367 creator A5078551585 @default.
- W2950470367 date "2017-10-27" @default.
- W2950470367 modified "2023-10-16" @default.
- W2950470367 title "Speeding up Context-based Sentence Representation Learning with Non-autoregressive Convolutional Decoding" @default.
- W2950470367 doi "https://doi.org/10.48550/arxiv.1710.10380" @default.
- W2950470367 hasPublicationYear "2017" @default.
- W2950470367 type Work @default.
- W2950470367 sameAs 2950470367 @default.
- W2950470367 citedByCount "0" @default.
- W2950470367 crossrefType "posted-content" @default.
- W2950470367 hasAuthorship W2950470367A5051364953 @default.
- W2950470367 hasAuthorship W2950470367A5063499488 @default.
- W2950470367 hasAuthorship W2950470367A5068625652 @default.
- W2950470367 hasAuthorship W2950470367A5071129405 @default.
- W2950470367 hasAuthorship W2950470367A5078551585 @default.
- W2950470367 hasBestOaLocation W29504703671 @default.
- W2950470367 hasConcept C111919701 @default.
- W2950470367 hasConcept C11413529 @default.
- W2950470367 hasConcept C118505674 @default.
- W2950470367 hasConcept C119857082 @default.
- W2950470367 hasConcept C137293760 @default.
- W2950470367 hasConcept C149782125 @default.
- W2950470367 hasConcept C151730666 @default.
- W2950470367 hasConcept C154945302 @default.
- W2950470367 hasConcept C159877910 @default.
- W2950470367 hasConcept C177264268 @default.
- W2950470367 hasConcept C17744445 @default.
- W2950470367 hasConcept C199360897 @default.
- W2950470367 hasConcept C199539241 @default.
- W2950470367 hasConcept C204321447 @default.
- W2950470367 hasConcept C2776359362 @default.
- W2950470367 hasConcept C2777530160 @default.
- W2950470367 hasConcept C2779343474 @default.
- W2950470367 hasConcept C28490314 @default.
- W2950470367 hasConcept C33923547 @default.
- W2950470367 hasConcept C41008148 @default.
- W2950470367 hasConcept C57273362 @default.
- W2950470367 hasConcept C86803240 @default.
- W2950470367 hasConcept C94625758 @default.
- W2950470367 hasConceptScore W2950470367C111919701 @default.
- W2950470367 hasConceptScore W2950470367C11413529 @default.
- W2950470367 hasConceptScore W2950470367C118505674 @default.
- W2950470367 hasConceptScore W2950470367C119857082 @default.
- W2950470367 hasConceptScore W2950470367C137293760 @default.
- W2950470367 hasConceptScore W2950470367C149782125 @default.
- W2950470367 hasConceptScore W2950470367C151730666 @default.
- W2950470367 hasConceptScore W2950470367C154945302 @default.
- W2950470367 hasConceptScore W2950470367C159877910 @default.
- W2950470367 hasConceptScore W2950470367C177264268 @default.
- W2950470367 hasConceptScore W2950470367C17744445 @default.
- W2950470367 hasConceptScore W2950470367C199360897 @default.
- W2950470367 hasConceptScore W2950470367C199539241 @default.
- W2950470367 hasConceptScore W2950470367C204321447 @default.
- W2950470367 hasConceptScore W2950470367C2776359362 @default.
- W2950470367 hasConceptScore W2950470367C2777530160 @default.
- W2950470367 hasConceptScore W2950470367C2779343474 @default.
- W2950470367 hasConceptScore W2950470367C28490314 @default.
- W2950470367 hasConceptScore W2950470367C33923547 @default.
- W2950470367 hasConceptScore W2950470367C41008148 @default.
- W2950470367 hasConceptScore W2950470367C57273362 @default.
- W2950470367 hasConceptScore W2950470367C86803240 @default.
- W2950470367 hasConceptScore W2950470367C94625758 @default.
- W2950470367 hasLocation W29504703671 @default.
- W2950470367 hasOpenAccess W2950470367 @default.
- W2950470367 hasPrimaryLocation W29504703671 @default.
- W2950470367 hasRelatedWork W1542956019 @default.
- W2950470367 hasRelatedWork W1846229318 @default.
- W2950470367 hasRelatedWork W2753086417 @default.
- W2950470367 hasRelatedWork W2798712174 @default.
- W2950470367 hasRelatedWork W3005895185 @default.
- W2950470367 hasRelatedWork W3107474891 @default.
- W2950470367 hasRelatedWork W3134587148 @default.
- W2950470367 hasRelatedWork W3148986242 @default.
- W2950470367 hasRelatedWork W3203408106 @default.
- W2950470367 hasRelatedWork W4226054021 @default.
- W2950470367 isParatext "false" @default.
- W2950470367 isRetracted "false" @default.
- W2950470367 magId "2950470367" @default.
- W2950470367 workType "article" @default.