FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3105203922> ?p ?o ?g. }

• W3105203922 abstract "Sarcasm detection in social media with text and image is becoming more challenging. Previous works of image-text sarcasm detection were mainly to fuse the summaries of text and image: different sub-models read the text and image respectively to get the summaries, and fuses the summaries. Recently, some multi-modal models based on the architecture of BERT are proposed such as ViLBERT. However, they can only be pretrained on the image-text data. In this paper, we propose an image-text model for sarcasm detection using the pretrained BERT and ResNet without any further pretraining. BERT and ResNet have been pretrained on much larger text or image data than image-text data. We connect the vector spaces of BERT and ResNet to utilize more data. We use the pretrained Multi-Head Attention of BERT to model the text and image. Besides, we propose a 2D-Intra-Attention to extract the relationships between words and images. In experiments, our model outperforms the state-of-the-art model." @default.
• W3105203922 created "2020-11-23" @default.
• W3105203922 creator A5003152439 @default.
• W3105203922 creator A5005380940 @default.
• W3105203922 creator A5010857597 @default.
• W3105203922 creator A5048956159 @default.
• W3105203922 date "2020-01-01" @default.
• W3105203922 modified "2023-10-16" @default.
• W3105203922 title "Building a Bridge: A Method for Image-Text Sarcasm Detection Without Pretraining on Image-Text Data" @default.
• W3105203922 cites W1677182931 @default.
• W3105203922 cites W1842080548 @default.
• W3105203922 cites W2024011160 @default.
• W3105203922 cites W2041400887 @default.
• W3105203922 cites W2064675550 @default.
• W3105203922 cites W2101234009 @default.
• W3105203922 cites W2114661483 @default.
• W3105203922 cites W2137527984 @default.
• W3105203922 cites W2157331557 @default.
• W3105203922 cites W2165044314 @default.
• W3105203922 cites W2194775991 @default.
• W3105203922 cites W2250489604 @default.
• W3105203922 cites W2250710744 @default.
• W3105203922 cites W2251210340 @default.
• W3105203922 cites W2251379416 @default.
• W3105203922 cites W2251920663 @default.
• W3105203922 cites W2263859238 @default.
• W3105203922 cites W2289385123 @default.
• W3105203922 cites W2489370933 @default.
• W3105203922 cites W2512470422 @default.
• W3105203922 cites W2512532697 @default.
• W3105203922 cites W2566622362 @default.
• W3105203922 cites W2575367545 @default.
• W3105203922 cites W2609193491 @default.
• W3105203922 cites W2758985501 @default.
• W3105203922 cites W2910191085 @default.
• W3105203922 cites W2962709202 @default.
• W3105203922 cites W2963341956 @default.
• W3105203922 cites W2963403868 @default.
• W3105203922 cites W2964010806 @default.
• W3105203922 cites W2964121744 @default.
• W3105203922 cites W2964126051 @default.
• W3105203922 cites W2964260444 @default.
• W3105203922 cites W2964266095 @default.
• W3105203922 cites W2965373594 @default.
• W3105203922 cites W2968124245 @default.
• W3105203922 cites W2969078176 @default.
• W3105203922 cites W2970217405 @default.
• W3105203922 cites W2970231061 @default.
• W3105203922 cites W2970608575 @default.
• W3105203922 cites W2970657565 @default.
• W3105203922 cites W2970869018 @default.
• W3105203922 cites W2970971581 @default.
• W3105203922 cites W2978017171 @default.
• W3105203922 cites W2985050637 @default.
• W3105203922 cites W2986660805 @default.
• W3105203922 cites W2996428491 @default.
• W3105203922 cites W3034727271 @default.
• W3105203922 cites W3106003309 @default.
• W3105203922 doi "https://doi.org/10.18653/v1/2020.nlpbt-1.3" @default.
• W3105203922 hasPublicationYear "2020" @default.
• W3105203922 type Work @default.
• W3105203922 sameAs 3105203922 @default.
• W3105203922 citedByCount "15" @default.
• W3105203922 countsByYear W31052039222021 @default.
• W3105203922 countsByYear W31052039222022 @default.
• W3105203922 countsByYear W31052039222023 @default.
• W3105203922 crossrefType "proceedings-article" @default.
• W3105203922 hasAuthorship W3105203922A5003152439 @default.
• W3105203922 hasAuthorship W3105203922A5005380940 @default.
• W3105203922 hasAuthorship W3105203922A5010857597 @default.
• W3105203922 hasAuthorship W3105203922A5048956159 @default.
• W3105203922 hasBestOaLocation W31052039221 @default.
• W3105203922 hasConcept C115961682 @default.
• W3105203922 hasConcept C119599485 @default.
• W3105203922 hasConcept C124952713 @default.
• W3105203922 hasConcept C127413603 @default.
• W3105203922 hasConcept C141353440 @default.
• W3105203922 hasConcept C142362112 @default.
• W3105203922 hasConcept C153180895 @default.
• W3105203922 hasConcept C154945302 @default.
• W3105203922 hasConcept C204321447 @default.
• W3105203922 hasConcept C2776207355 @default.
• W3105203922 hasConcept C2779975665 @default.
• W3105203922 hasConcept C31972630 @default.
• W3105203922 hasConcept C41008148 @default.
• W3105203922 hasConceptScore W3105203922C115961682 @default.
• W3105203922 hasConceptScore W3105203922C119599485 @default.
• W3105203922 hasConceptScore W3105203922C124952713 @default.
• W3105203922 hasConceptScore W3105203922C127413603 @default.
• W3105203922 hasConceptScore W3105203922C141353440 @default.
• W3105203922 hasConceptScore W3105203922C142362112 @default.
• W3105203922 hasConceptScore W3105203922C153180895 @default.
• W3105203922 hasConceptScore W3105203922C154945302 @default.
• W3105203922 hasConceptScore W3105203922C204321447 @default.
• W3105203922 hasConceptScore W3105203922C2776207355 @default.
• W3105203922 hasConceptScore W3105203922C2779975665 @default.
• W3105203922 hasConceptScore W3105203922C31972630 @default.
• W3105203922 hasConceptScore W3105203922C41008148 @default.
• W3105203922 hasLocation W31052039221 @default.
• W3105203922 hasOpenAccess W3105203922 @default.

• next