Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386811881> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4386811881 endingPage "141" @default.
- W4386811881 startingPage "124" @default.
- W4386811881 abstract "Abstractive text summarization has been of research interest for decades. Neural approaches, specifically recent transformer-based methods, have demonstrated promising performance in generating summaries with novel words and paraphrases. In spite of generating more fluent summaries, these approaches may yet show poor summary-worthy content selection. In these methods, the extractive content selection is majorly dependent on the reference summary with little to no focus on identifying the summary-worthy segments (SWORTS) in a reference-free setting. In this work, we leverage three metrics, namely, informativeness, relevance, and redundancy in selecting the SWORTS. We propose a novel topic-informed and reference-free method to rank the sentences in the source document based on their importance. We demonstrate the effectiveness of SWORTS selection in different settings such as fine-tuning, few-shot tuning, and zero-shot abstractive text summarization. We observe that self-training and cross-training a pre-trained model with SWORTS selected data shows competitive performance to the pre-trained model. Furthermore, a small amount of SWORTS selected data is sufficient for domain adaptation against fine-tuning on the entire training dataset with no content selection. In contrast to training a model on the source dataset with no content selection, we observe a significant reduction in the time required to train a model with SWORTS that further underlines the importance of content selection for training an abstractive text summarization model." @default.
- W4386811881 created "2023-09-18" @default.
- W4386811881 creator A5063165677 @default.
- W4386811881 creator A5070671075 @default.
- W4386811881 creator A5086177621 @default.
- W4386811881 date "2023-01-01" @default.
- W4386811881 modified "2023-10-16" @default.
- W4386811881 title "A Few Good Sentences: Content Selection for Abstractive Text Summarization" @default.
- W4386811881 cites W2153353890 @default.
- W4386811881 cites W2307381258 @default.
- W4386811881 cites W2888482885 @default.
- W4386811881 cites W2889518897 @default.
- W4386811881 cites W2949807892 @default.
- W4386811881 cites W2952138241 @default.
- W4386811881 cites W2952215948 @default.
- W4386811881 cites W2962972512 @default.
- W4386811881 cites W2962985882 @default.
- W4386811881 cites W2963326042 @default.
- W4386811881 cites W2963929190 @default.
- W4386811881 cites W2964125718 @default.
- W4386811881 cites W2970600560 @default.
- W4386811881 cites W2970641574 @default.
- W4386811881 cites W2970785793 @default.
- W4386811881 cites W2982756875 @default.
- W4386811881 cites W2985808369 @default.
- W4386811881 cites W2989743967 @default.
- W4386811881 cites W3034999214 @default.
- W4386811881 cites W3035050380 @default.
- W4386811881 cites W3098968529 @default.
- W4386811881 cites W3101693329 @default.
- W4386811881 cites W3103417625 @default.
- W4386811881 cites W3106445907 @default.
- W4386811881 cites W3152969993 @default.
- W4386811881 cites W3173210704 @default.
- W4386811881 cites W3175378952 @default.
- W4386811881 cites W3176503701 @default.
- W4386811881 cites W3176778415 @default.
- W4386811881 cites W4225117647 @default.
- W4386811881 cites W4385567098 @default.
- W4386811881 cites W4385572377 @default.
- W4386811881 cites W4385574315 @default.
- W4386811881 doi "https://doi.org/10.1007/978-3-031-43421-1_8" @default.
- W4386811881 hasPublicationYear "2023" @default.
- W4386811881 type Work @default.
- W4386811881 citedByCount "0" @default.
- W4386811881 crossrefType "book-chapter" @default.
- W4386811881 hasAuthorship W4386811881A5063165677 @default.
- W4386811881 hasAuthorship W4386811881A5070671075 @default.
- W4386811881 hasAuthorship W4386811881A5086177621 @default.
- W4386811881 hasConcept C111919701 @default.
- W4386811881 hasConcept C119857082 @default.
- W4386811881 hasConcept C121332964 @default.
- W4386811881 hasConcept C152124472 @default.
- W4386811881 hasConcept C153083717 @default.
- W4386811881 hasConcept C154945302 @default.
- W4386811881 hasConcept C165801399 @default.
- W4386811881 hasConcept C170858558 @default.
- W4386811881 hasConcept C204321447 @default.
- W4386811881 hasConcept C23123220 @default.
- W4386811881 hasConcept C41008148 @default.
- W4386811881 hasConcept C62520636 @default.
- W4386811881 hasConcept C66322947 @default.
- W4386811881 hasConcept C81917197 @default.
- W4386811881 hasConceptScore W4386811881C111919701 @default.
- W4386811881 hasConceptScore W4386811881C119857082 @default.
- W4386811881 hasConceptScore W4386811881C121332964 @default.
- W4386811881 hasConceptScore W4386811881C152124472 @default.
- W4386811881 hasConceptScore W4386811881C153083717 @default.
- W4386811881 hasConceptScore W4386811881C154945302 @default.
- W4386811881 hasConceptScore W4386811881C165801399 @default.
- W4386811881 hasConceptScore W4386811881C170858558 @default.
- W4386811881 hasConceptScore W4386811881C204321447 @default.
- W4386811881 hasConceptScore W4386811881C23123220 @default.
- W4386811881 hasConceptScore W4386811881C41008148 @default.
- W4386811881 hasConceptScore W4386811881C62520636 @default.
- W4386811881 hasConceptScore W4386811881C66322947 @default.
- W4386811881 hasConceptScore W4386811881C81917197 @default.
- W4386811881 hasLocation W43868118811 @default.
- W4386811881 hasOpenAccess W4386811881 @default.
- W4386811881 hasPrimaryLocation W43868118811 @default.
- W4386811881 hasRelatedWork W132250100 @default.
- W4386811881 hasRelatedWork W1546239215 @default.
- W4386811881 hasRelatedWork W2093597205 @default.
- W4386811881 hasRelatedWork W2389846579 @default.
- W4386811881 hasRelatedWork W2392495745 @default.
- W4386811881 hasRelatedWork W2401226416 @default.
- W4386811881 hasRelatedWork W2725657302 @default.
- W4386811881 hasRelatedWork W4221140906 @default.
- W4386811881 hasRelatedWork W4308478176 @default.
- W4386811881 hasRelatedWork W2129073325 @default.
- W4386811881 isParatext "false" @default.
- W4386811881 isRetracted "false" @default.
- W4386811881 workType "book-chapter" @default.