FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3128687455> ?p ?o ?g. }

• W3128687455 endingPage "148" @default.
• W3128687455 startingPage "130" @default.
• W3128687455 abstract "Neural sequence to sequence models have achieved superlative performance in summarizing text. But they tend to generate generic summaries that under-represent the opinion-sensitive aspects of the document. Additionally, the sequence to sequence models are prone to test-train discrepancy (exposure-bias) arising from the differential summary decoding processes in the training and testing phases. The models use ground truth summary words in the decoder training phase and predicted outputs in the testing phase. This inconsistency leads to error accumulation and substandard performance. To address these gaps, a cognitive aspect-based opinion summarizer, Feature Pooled Pointer Generator Network (FP2GN), is proposed which selectively attends to thematic and contextual cues to generate sentiment-aware review summaries. This study augments the pointer generator framework with opinion feature extraction, feature pooling, and mutual attention mechanism for opinion summarization. The proposed model FP2GN identifies the aspect terms in review text using sentic computing (SenticNet 5 and concept frequency-inverse opinion frequency) and statistical feature engineering. These aspect terms are encoded into context embeddings using weighted average feature pooling, which is processed in a pointer-generator framework inspired stacked Bi-LSTM encoder–decoder model with multi-head self-attention. The decoder system uses temporal and mutual attention mechanisms to ensure the appropriate representation of input-sequence. The study also proffers the use of teacher forcing ratio to curtail the exposure-bias-related error-accumulation. The model achieves ROUGE-1 score of 86.04% and ROUGE-L score of 88.51% on the Amazon Fine Foods dataset. An average gain of 2% over other methods is observed. The proposed model reinforces pointer generator network architecture with opinion feature extraction, feature pooling, and mutual attention mechanism to generate human-readable opinion summaries. Empirical analysis substantiates that the proposed model is better than the baseline opinion summarizers." @default.
• W3128687455 created "2021-02-15" @default.
• W3128687455 creator A5026345348 @default.
• W3128687455 creator A5042471916 @default.
• W3128687455 creator A5046087654 @default.
• W3128687455 creator A5089321748 @default.
• W3128687455 date "2021-02-04" @default.
• W3128687455 modified "2023-09-23" @default.
• W3128687455 title "Sentic Computing for Aspect-Based Opinion Summarization Using Multi-Head Attention with Feature Pooled Pointer Generator Network" @default.
• W3128687455 cites W1054465322 @default.
• W3128687455 cites W1618595639 @default.
• W3128687455 cites W1868188096 @default.
• W3128687455 cites W1995953117 @default.
• W3128687455 cites W2016589492 @default.
• W3128687455 cites W2019109450 @default.
• W3128687455 cites W2020060453 @default.
• W3128687455 cites W2064675550 @default.
• W3128687455 cites W2096044513 @default.
• W3128687455 cites W2106813246 @default.
• W3128687455 cites W2108300325 @default.
• W3128687455 cites W2136891251 @default.
• W3128687455 cites W2143017621 @default.
• W3128687455 cites W2192604218 @default.
• W3128687455 cites W2251202616 @default.
• W3128687455 cites W2606937156 @default.
• W3128687455 cites W2606974598 @default.
• W3128687455 cites W2766718178 @default.
• W3128687455 cites W2780842565 @default.
• W3128687455 cites W2783821110 @default.
• W3128687455 cites W2786411768 @default.
• W3128687455 cites W2788810909 @default.
• W3128687455 cites W2788967885 @default.
• W3128687455 cites W2792089754 @default.
• W3128687455 cites W2896820601 @default.
• W3128687455 cites W2925065304 @default.
• W3128687455 cites W2946015932 @default.
• W3128687455 cites W2949202718 @default.
• W3128687455 cites W2952138241 @default.
• W3128687455 cites W2963521413 @default.
• W3128687455 cites W2963929190 @default.
• W3128687455 cites W2964300796 @default.
• W3128687455 cites W2965727955 @default.
• W3128687455 cites W2972350567 @default.
• W3128687455 cites W2973572715 @default.
• W3128687455 cites W2977413186 @default.
• W3128687455 cites W2978189281 @default.
• W3128687455 cites W2978806970 @default.
• W3128687455 cites W2980480643 @default.
• W3128687455 cites W2980806126 @default.
• W3128687455 cites W2989747620 @default.
• W3128687455 cites W2998517938 @default.
• W3128687455 cites W3005378242 @default.
• W3128687455 cites W3012172056 @default.
• W3128687455 cites W3012246690 @default.
• W3128687455 cites W3012254375 @default.
• W3128687455 cites W3094173182 @default.
• W3128687455 cites W3094384122 @default.
• W3128687455 cites W3094412822 @default.
• W3128687455 doi "https://doi.org/10.1007/s12559-021-09835-8" @default.
• W3128687455 hasPublicationYear "2021" @default.
• W3128687455 type Work @default.
• W3128687455 sameAs 3128687455 @default.
• W3128687455 citedByCount "5" @default.
• W3128687455 countsByYear W31286874552021 @default.
• W3128687455 countsByYear W31286874552022 @default.
• W3128687455 countsByYear W31286874552023 @default.
• W3128687455 crossrefType "journal-article" @default.
• W3128687455 hasAuthorship W3128687455A5026345348 @default.
• W3128687455 hasAuthorship W3128687455A5042471916 @default.
• W3128687455 hasAuthorship W3128687455A5046087654 @default.
• W3128687455 hasAuthorship W3128687455A5089321748 @default.
• W3128687455 hasBestOaLocation W31286874552 @default.
• W3128687455 hasConcept C111919701 @default.
• W3128687455 hasConcept C118505674 @default.
• W3128687455 hasConcept C119857082 @default.
• W3128687455 hasConcept C138885662 @default.
• W3128687455 hasConcept C150202949 @default.
• W3128687455 hasConcept C153180895 @default.
• W3128687455 hasConcept C154945302 @default.
• W3128687455 hasConcept C170858558 @default.
• W3128687455 hasConcept C204321447 @default.
• W3128687455 hasConcept C2776401178 @default.
• W3128687455 hasConcept C28490314 @default.
• W3128687455 hasConcept C41008148 @default.
• W3128687455 hasConcept C41895202 @default.
• W3128687455 hasConcept C66402592 @default.
• W3128687455 hasConcept C70437156 @default.
• W3128687455 hasConceptScore W3128687455C111919701 @default.
• W3128687455 hasConceptScore W3128687455C118505674 @default.
• W3128687455 hasConceptScore W3128687455C119857082 @default.
• W3128687455 hasConceptScore W3128687455C138885662 @default.
• W3128687455 hasConceptScore W3128687455C150202949 @default.
• W3128687455 hasConceptScore W3128687455C153180895 @default.
• W3128687455 hasConceptScore W3128687455C154945302 @default.
• W3128687455 hasConceptScore W3128687455C170858558 @default.
• W3128687455 hasConceptScore W3128687455C204321447 @default.
• W3128687455 hasConceptScore W3128687455C2776401178 @default.
• W3128687455 hasConceptScore W3128687455C28490314 @default.

• next