Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313347139> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W4313347139 abstract "Cross-lingual summarization (CLS) is a process of generating a summary in the target language from a source document in another language. CLS is a challenging task because it involves two different languages. Traditionally, CLS is carried out in a pipeline scheme that involves two steps: summarization and translation. This approach has a problem, it introduces error propagation. To address this problem, we present a novel end-to-end abstractive CLS without the explicit use of machine translation. The CLS architecture is based on Transformer which is proven to be able to perform text generation well. The CLS model is a jointly trained CLS task and monolingual summarization (MS) task. This is accomplished by adding a second decoder to handle the MS task, while the first decoder handles the CLS task. We also incorporated multilingual word embeddings (MWE) components into the architecture to further improve the performance of the CLS models. Both English and Bahasa Indonesia are represented by MWE whose embeddings have already been mapped into the same vector space. MWE helps to better map the relation between input and output that use different languages. Experiments show that the proposed model achieves improvement up to +0.2981 ROUGE-1, +0.2084 ROUGE-2, and +0.2771 ROUGE-L when compared to the pipeline baselines and up to +0.1288 ROUGE-1, +0.1185 ROUGE-2, and +0.1413 ROUGE-L when compared to the end-to-end baselines." @default.
- W4313347139 created "2023-01-06" @default.
- W4313347139 creator A5066073372 @default.
- W4313347139 creator A5068825317 @default.
- W4313347139 creator A5069933043 @default.
- W4313347139 date "2022-01-01" @default.
- W4313347139 modified "2023-09-30" @default.
- W4313347139 title "Transformer-based Cross-Lingual Summarization using Multilingual Word Embeddings for English - Bahasa Indonesia" @default.
- W4313347139 doi "https://doi.org/10.14569/ijacsa.2022.0131276" @default.
- W4313347139 hasPublicationYear "2022" @default.
- W4313347139 type Work @default.
- W4313347139 citedByCount "0" @default.
- W4313347139 crossrefType "journal-article" @default.
- W4313347139 hasAuthorship W4313347139A5066073372 @default.
- W4313347139 hasAuthorship W4313347139A5068825317 @default.
- W4313347139 hasAuthorship W4313347139A5069933043 @default.
- W4313347139 hasBestOaLocation W43133471391 @default.
- W4313347139 hasConcept C11413529 @default.
- W4313347139 hasConcept C119767625 @default.
- W4313347139 hasConcept C121332964 @default.
- W4313347139 hasConcept C154945302 @default.
- W4313347139 hasConcept C162324750 @default.
- W4313347139 hasConcept C165801399 @default.
- W4313347139 hasConcept C170858558 @default.
- W4313347139 hasConcept C187736073 @default.
- W4313347139 hasConcept C190729725 @default.
- W4313347139 hasConcept C199360897 @default.
- W4313347139 hasConcept C203005215 @default.
- W4313347139 hasConcept C204321447 @default.
- W4313347139 hasConcept C2780451532 @default.
- W4313347139 hasConcept C28490314 @default.
- W4313347139 hasConcept C41008148 @default.
- W4313347139 hasConcept C43521106 @default.
- W4313347139 hasConcept C57273362 @default.
- W4313347139 hasConcept C62520636 @default.
- W4313347139 hasConcept C66322947 @default.
- W4313347139 hasConcept C71924100 @default.
- W4313347139 hasConceptScore W4313347139C11413529 @default.
- W4313347139 hasConceptScore W4313347139C119767625 @default.
- W4313347139 hasConceptScore W4313347139C121332964 @default.
- W4313347139 hasConceptScore W4313347139C154945302 @default.
- W4313347139 hasConceptScore W4313347139C162324750 @default.
- W4313347139 hasConceptScore W4313347139C165801399 @default.
- W4313347139 hasConceptScore W4313347139C170858558 @default.
- W4313347139 hasConceptScore W4313347139C187736073 @default.
- W4313347139 hasConceptScore W4313347139C190729725 @default.
- W4313347139 hasConceptScore W4313347139C199360897 @default.
- W4313347139 hasConceptScore W4313347139C203005215 @default.
- W4313347139 hasConceptScore W4313347139C204321447 @default.
- W4313347139 hasConceptScore W4313347139C2780451532 @default.
- W4313347139 hasConceptScore W4313347139C28490314 @default.
- W4313347139 hasConceptScore W4313347139C41008148 @default.
- W4313347139 hasConceptScore W4313347139C43521106 @default.
- W4313347139 hasConceptScore W4313347139C57273362 @default.
- W4313347139 hasConceptScore W4313347139C62520636 @default.
- W4313347139 hasConceptScore W4313347139C66322947 @default.
- W4313347139 hasConceptScore W4313347139C71924100 @default.
- W4313347139 hasIssue "12" @default.
- W4313347139 hasLocation W43133471391 @default.
- W4313347139 hasOpenAccess W4313347139 @default.
- W4313347139 hasPrimaryLocation W43133471391 @default.
- W4313347139 hasRelatedWork W1512718085 @default.
- W4313347139 hasRelatedWork W2058999950 @default.
- W4313347139 hasRelatedWork W2129683077 @default.
- W4313347139 hasRelatedWork W2917049097 @default.
- W4313347139 hasRelatedWork W2971411184 @default.
- W4313347139 hasRelatedWork W4281385036 @default.
- W4313347139 hasRelatedWork W4284703357 @default.
- W4313347139 hasRelatedWork W4360585598 @default.
- W4313347139 hasRelatedWork W4361804203 @default.
- W4313347139 hasRelatedWork W2610387714 @default.
- W4313347139 hasVolume "13" @default.
- W4313347139 isParatext "false" @default.
- W4313347139 isRetracted "false" @default.
- W4313347139 workType "article" @default.