FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3169565655> ?p ?o ?g. }

• W3169565655 abstract "State-of-the-art abstractive summarization models generally rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available. In this paper, we present a study of domain adaptation for the abstractive summarization task across six diverse target domains in a low-resource setting. Specifically, we investigate the second phase of pre-training on large-scale generative models under three different settings: 1) source domain pre-training; 2) domain-adaptive pre-training; and 3) task-adaptive pre-training. Experiments show that the effectiveness of pre-training is correlated with the similarity between the pre-training data and the target domain task. Moreover, we find that continuing pre-training could lead to the pre-trained model’s catastrophic forgetting, and a learning method with less forgetting can alleviate this issue. Furthermore, results illustrate that a huge gap still exists between the low-resource and high-resource settings, which highlights the need for more advanced domain adaptation methods for the abstractive summarization task." @default.
• W3169565655 created "2021-06-22" @default.
• W3169565655 creator A5011760791 @default.
• W3169565655 creator A5065856469 @default.
• W3169565655 creator A5081246075 @default.
• W3169565655 date "2021-01-01" @default.
• W3169565655 modified "2023-09-30" @default.
• W3169565655 title "AdaptSum: Towards Low-Resource Domain Adaptation for Abstractive Summarization" @default.
• W3169565655 cites W1531174292 @default.
• W3169565655 cites W1544827683 @default.
• W3169565655 cites W1848260265 @default.
• W3169565655 cites W2105523772 @default.
• W3169565655 cites W2113459411 @default.
• W3169565655 cites W2120354757 @default.
• W3169565655 cites W2130942839 @default.
• W3169565655 cites W2163302275 @default.
• W3169565655 cites W2560647685 @default.
• W3169565655 cites W2606974598 @default.
• W3169565655 cites W2612675303 @default.
• W3169565655 cites W2888482885 @default.
• W3169565655 cites W2889518897 @default.
• W3169565655 cites W2911489562 @default.
• W3169565655 cites W2953209111 @default.
• W3169565655 cites W2962724315 @default.
• W3169565655 cites W2962739339 @default.
• W3169565655 cites W2962788840 @default.
• W3169565655 cites W2962985882 @default.
• W3169565655 cites W2963260202 @default.
• W3169565655 cites W2963275094 @default.
• W3169565655 cites W2963310665 @default.
• W3169565655 cites W2963341956 @default.
• W3169565655 cites W2963443217 @default.
• W3169565655 cites W2963475460 @default.
• W3169565655 cites W2963721761 @default.
• W3169565655 cites W2963825865 @default.
• W3169565655 cites W2963929190 @default.
• W3169565655 cites W2964121744 @default.
• W3169565655 cites W2964288227 @default.
• W3169565655 cites W2965373594 @default.
• W3169565655 cites W2970060597 @default.
• W3169565655 cites W2970419734 @default.
• W3169565655 cites W2970771982 @default.
• W3169565655 cites W2971160427 @default.
• W3169565655 cites W2971274815 @default.
• W3169565655 cites W2972111982 @default.
• W3169565655 cites W2989743967 @default.
• W3169565655 cites W2996428491 @default.
• W3169565655 cites W2997214274 @default.
• W3169565655 cites W3010079431 @default.
• W3169565655 cites W3023047914 @default.
• W3169565655 cites W3034238471 @default.
• W3169565655 cites W3034238904 @default.
• W3169565655 cites W3037541622 @default.
• W3169565655 cites W3037747687 @default.
• W3169565655 cites W3043372854 @default.
• W3169565655 cites W3049433044 @default.
• W3169565655 cites W3082274269 @default.
• W3169565655 cites W3092803162 @default.
• W3169565655 cites W3104215796 @default.
• W3169565655 doi "https://doi.org/10.18653/v1/2021.naacl-main.471" @default.
• W3169565655 hasPublicationYear "2021" @default.
• W3169565655 type Work @default.
• W3169565655 sameAs 3169565655 @default.
• W3169565655 citedByCount "22" @default.
• W3169565655 countsByYear W31695656552021 @default.
• W3169565655 countsByYear W31695656552022 @default.
• W3169565655 countsByYear W31695656552023 @default.
• W3169565655 crossrefType "proceedings-article" @default.
• W3169565655 hasAuthorship W3169565655A5011760791 @default.
• W3169565655 hasAuthorship W3169565655A5065856469 @default.
• W3169565655 hasAuthorship W3169565655A5081246075 @default.
• W3169565655 hasBestOaLocation W31695656551 @default.
• W3169565655 hasConcept C103278499 @default.
• W3169565655 hasConcept C115961682 @default.
• W3169565655 hasConcept C119857082 @default.
• W3169565655 hasConcept C120665830 @default.
• W3169565655 hasConcept C121332964 @default.
• W3169565655 hasConcept C134306372 @default.
• W3169565655 hasConcept C139807058 @default.
• W3169565655 hasConcept C154945302 @default.
• W3169565655 hasConcept C15744967 @default.
• W3169565655 hasConcept C162324750 @default.
• W3169565655 hasConcept C170858558 @default.
• W3169565655 hasConcept C177148314 @default.
• W3169565655 hasConcept C180747234 @default.
• W3169565655 hasConcept C187736073 @default.
• W3169565655 hasConcept C204321447 @default.
• W3169565655 hasConcept C206345919 @default.
• W3169565655 hasConcept C2776434776 @default.
• W3169565655 hasConcept C2780451532 @default.
• W3169565655 hasConcept C31258907 @default.
• W3169565655 hasConcept C33923547 @default.
• W3169565655 hasConcept C36503486 @default.
• W3169565655 hasConcept C39890363 @default.
• W3169565655 hasConcept C41008148 @default.
• W3169565655 hasConcept C7149132 @default.
• W3169565655 hasConcept C95623464 @default.
• W3169565655 hasConceptScore W3169565655C103278499 @default.
• W3169565655 hasConceptScore W3169565655C115961682 @default.
• W3169565655 hasConceptScore W3169565655C119857082 @default.

• next