FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3035576805> ?p ?o ?g. }

• W3035576805 abstract "The supervised training of high-capacity models on large datasets containing hundreds of thousands of document-summary pairs is critical to the recent success of deep learning techniques for abstractive summarization. Unfortunately, in most domains (other than news) such training data is not available and cannot be easily sourced. In this paper we enable the use of supervised learning for the setting where there are only documents available (e.g., product or business reviews) without ground truth summaries. We create a synthetic dataset from a corpus of user reviews by sampling a review, pretending it is a summary, and generating noisy versions thereof which we treat as pseudo-review input. We introduce several linguistically motivated noise generation functions and a summarization model which learns to denoise the input and generate the original review. At test time, the model accepts genuine reviews and generates a summary containing salient opinions, treating those that do not reach consensus as noise. Extensive automatic and human evaluation shows that our model brings substantial improvements over both abstractive and extractive baselines." @default.
• W3035576805 created "2020-06-19" @default.
• W3035576805 creator A5009993083 @default.
• W3035576805 creator A5041024491 @default.
• W3035576805 date "2020-01-01" @default.
• W3035576805 modified "2023-10-16" @default.
• W3035576805 title "Unsupervised Opinion Summarization with Noising and Denoising" @default.
• W3035576805 cites W1544827683 @default.
• W3035576805 cites W1569041844 @default.
• W3035576805 cites W1880262756 @default.
• W3035576805 cites W1939882552 @default.
• W3035576805 cites W1978078764 @default.
• W3035576805 cites W2025768430 @default.
• W3035576805 cites W2064675550 @default.
• W3035576805 cites W2095705004 @default.
• W3035576805 cites W2097726431 @default.
• W3035576805 cites W2114524997 @default.
• W3035576805 cites W2128507180 @default.
• W3035576805 cites W2128672521 @default.
• W3035576805 cites W2133459682 @default.
• W3035576805 cites W2134854314 @default.
• W3035576805 cites W2145071407 @default.
• W3035576805 cites W2148404145 @default.
• W3035576805 cites W2154652894 @default.
• W3035576805 cites W2165698076 @default.
• W3035576805 cites W2166706824 @default.
• W3035576805 cites W2250742840 @default.
• W3035576805 cites W2250864115 @default.
• W3035576805 cites W2270627573 @default.
• W3035576805 cites W22861983 @default.
• W3035576805 cites W2399573548 @default.
• W3035576805 cites W2507756961 @default.
• W3035576805 cites W2606347107 @default.
• W3035576805 cites W2606974598 @default.
• W3035576805 cites W2740656274 @default.
• W3035576805 cites W2888507208 @default.
• W3035576805 cites W2889518897 @default.
• W3035576805 cites W2950670227 @default.
• W3035576805 cites W2951835712 @default.
• W3035576805 cites W2955471745 @default.
• W3035576805 cites W2962739339 @default.
• W3035576805 cites W2962768052 @default.
• W3035576805 cites W2962849707 @default.
• W3035576805 cites W2962965405 @default.
• W3035576805 cites W2963045354 @default.
• W3035576805 cites W2963047186 @default.
• W3035576805 cites W2963204221 @default.
• W3035576805 cites W2963223306 @default.
• W3035576805 cites W2963385935 @default.
• W3035576805 cites W2963721761 @default.
• W3035576805 cites W2964121744 @default.
• W3035576805 cites W2964308564 @default.
• W3035576805 cites W2972057793 @default.
• W3035576805 cites W2985050317 @default.
• W3035576805 cites W2996287690 @default.
• W3035576805 cites W3101913037 @default.
• W3035576805 cites W3158986179 @default.
• W3035576805 cites W45569842 @default.
• W3035576805 doi "https://doi.org/10.18653/v1/2020.acl-main.175" @default.
• W3035576805 hasPublicationYear "2020" @default.
• W3035576805 type Work @default.
• W3035576805 sameAs 3035576805 @default.
• W3035576805 citedByCount "42" @default.
• W3035576805 countsByYear W30355768052019 @default.
• W3035576805 countsByYear W30355768052020 @default.
• W3035576805 countsByYear W30355768052021 @default.
• W3035576805 countsByYear W30355768052022 @default.
• W3035576805 countsByYear W30355768052023 @default.
• W3035576805 crossrefType "proceedings-article" @default.
• W3035576805 hasAuthorship W3035576805A5009993083 @default.
• W3035576805 hasAuthorship W3035576805A5041024491 @default.
• W3035576805 hasBestOaLocation W30355768051 @default.
• W3035576805 hasConcept C108583219 @default.
• W3035576805 hasConcept C115961682 @default.
• W3035576805 hasConcept C119857082 @default.
• W3035576805 hasConcept C124101348 @default.
• W3035576805 hasConcept C146849305 @default.
• W3035576805 hasConcept C154945302 @default.
• W3035576805 hasConcept C163294075 @default.
• W3035576805 hasConcept C170858558 @default.
• W3035576805 hasConcept C204321447 @default.
• W3035576805 hasConcept C23123220 @default.
• W3035576805 hasConcept C2522767166 @default.
• W3035576805 hasConcept C2780719617 @default.
• W3035576805 hasConcept C41008148 @default.
• W3035576805 hasConcept C99498987 @default.
• W3035576805 hasConceptScore W3035576805C108583219 @default.
• W3035576805 hasConceptScore W3035576805C115961682 @default.
• W3035576805 hasConceptScore W3035576805C119857082 @default.
• W3035576805 hasConceptScore W3035576805C124101348 @default.
• W3035576805 hasConceptScore W3035576805C146849305 @default.
• W3035576805 hasConceptScore W3035576805C154945302 @default.
• W3035576805 hasConceptScore W3035576805C163294075 @default.
• W3035576805 hasConceptScore W3035576805C170858558 @default.
• W3035576805 hasConceptScore W3035576805C204321447 @default.
• W3035576805 hasConceptScore W3035576805C23123220 @default.
• W3035576805 hasConceptScore W3035576805C2522767166 @default.
• W3035576805 hasConceptScore W3035576805C2780719617 @default.
• W3035576805 hasConceptScore W3035576805C41008148 @default.
• W3035576805 hasConceptScore W3035576805C99498987 @default.

• next