Matches in SemOpenAlex for { <https://semopenalex.org/work/W3132777673> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W3132777673 abstract "Self-attention networks (SANs) have shown promising empirical results in various natural language processing tasks. Typically, it gradually learning language knowledge on the whole training dataset in parallel and stacked ways, thereby modeling language representation. In this paper, we propose a simple and general representation method to consider prior knowledge related to language representation from the beginning of training. Also, the proposed method allows SANs to leverage prior knowledge in a universal way compatible with neural networks. Furthermore, we apply it to one prior word frequency knowledge for the monolingual data and other prior translation lexicon knowledge for the bilingual data, respectively, thereby enhancing the language representation. Experimental results on WMT14 English-to-German and WMT17 Chinese-to-English translation tasks demonstrate the effectiveness and universality of the proposed method over a strong Transformer-based baseline." @default.
- W3132777673 created "2021-03-01" @default.
- W3132777673 creator A5006323375 @default.
- W3132777673 creator A5021667085 @default.
- W3132777673 creator A5033318800 @default.
- W3132777673 creator A5070812231 @default.
- W3132777673 date "2021-05-04" @default.
- W3132777673 modified "2023-09-27" @default.
- W3132777673 title "Prior Knowledge Representation for Self-Attention Networks" @default.
- W3132777673 hasPublicationYear "2021" @default.
- W3132777673 type Work @default.
- W3132777673 sameAs 3132777673 @default.
- W3132777673 citedByCount "0" @default.
- W3132777673 crossrefType "journal-article" @default.
- W3132777673 hasAuthorship W3132777673A5006323375 @default.
- W3132777673 hasAuthorship W3132777673A5021667085 @default.
- W3132777673 hasAuthorship W3132777673A5033318800 @default.
- W3132777673 hasAuthorship W3132777673A5070812231 @default.
- W3132777673 hasConcept C119857082 @default.
- W3132777673 hasConcept C153083717 @default.
- W3132777673 hasConcept C154945302 @default.
- W3132777673 hasConcept C161301231 @default.
- W3132777673 hasConcept C203005215 @default.
- W3132777673 hasConcept C204321447 @default.
- W3132777673 hasConcept C2778121359 @default.
- W3132777673 hasConcept C41008148 @default.
- W3132777673 hasConcept C50644808 @default.
- W3132777673 hasConceptScore W3132777673C119857082 @default.
- W3132777673 hasConceptScore W3132777673C153083717 @default.
- W3132777673 hasConceptScore W3132777673C154945302 @default.
- W3132777673 hasConceptScore W3132777673C161301231 @default.
- W3132777673 hasConceptScore W3132777673C203005215 @default.
- W3132777673 hasConceptScore W3132777673C204321447 @default.
- W3132777673 hasConceptScore W3132777673C2778121359 @default.
- W3132777673 hasConceptScore W3132777673C41008148 @default.
- W3132777673 hasConceptScore W3132777673C50644808 @default.
- W3132777673 hasLocation W31327776731 @default.
- W3132777673 hasOpenAccess W3132777673 @default.
- W3132777673 hasPrimaryLocation W31327776731 @default.
- W3132777673 hasRelatedWork W2020833137 @default.
- W3132777673 hasRelatedWork W2074790252 @default.
- W3132777673 hasRelatedWork W2122993045 @default.
- W3132777673 hasRelatedWork W2160581145 @default.
- W3132777673 hasRelatedWork W2559703163 @default.
- W3132777673 hasRelatedWork W2621841989 @default.
- W3132777673 hasRelatedWork W2738396332 @default.
- W3132777673 hasRelatedWork W2892354565 @default.
- W3132777673 hasRelatedWork W2963578424 @default.
- W3132777673 hasRelatedWork W2970682957 @default.
- W3132777673 hasRelatedWork W2983772459 @default.
- W3132777673 hasRelatedWork W3035589854 @default.
- W3132777673 hasRelatedWork W3089262807 @default.
- W3132777673 hasRelatedWork W3093843097 @default.
- W3132777673 hasRelatedWork W3113462843 @default.
- W3132777673 hasRelatedWork W3114916066 @default.
- W3132777673 hasRelatedWork W3128860318 @default.
- W3132777673 hasRelatedWork W3170522022 @default.
- W3132777673 hasRelatedWork W3181088491 @default.
- W3132777673 hasRelatedWork W3210250266 @default.
- W3132777673 isParatext "false" @default.
- W3132777673 isRetracted "false" @default.
- W3132777673 magId "3132777673" @default.
- W3132777673 workType "article" @default.