FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213441645> ?p ?o ?g. }

• W3213441645 abstract "Unlike well-structured text, such as news reports and encyclopedia articles, dialogue content often comes from two or more interlocutors, exchanging information with each other. In such a scenario, the topic of a conversation can vary upon progression and the key information for a certain topic is often scattered across multiple utterances of different speakers, which poses challenges to abstractly summarize dialogues. To capture the various topic information of a conversation and outline salient facts for the captured topics, this work proposes two topic-aware contrastive learning objectives, namely coherence detection and sub-summary generation objectives, which are expected to implicitly model the topic change and handle information scattering challenges for the dialogue summarization task. The proposed contrastive objectives are framed as auxiliary tasks for the primary dialogue summarization task, united via an alternative parameter updating strategy. Extensive experiments on benchmark datasets demonstrate that the proposed simple method significantly outperforms strong baselines and achieves new state-of-the-art performance. The code and trained models are publicly available via href{https://github.com/Junpliu/ConDigSum}{https://github.com/Junpliu/ConDigSum}." @default.
• W3213441645 created "2021-11-22" @default.
• W3213441645 creator A5008043408 @default.
• W3213441645 creator A5041432735 @default.
• W3213441645 creator A5050030131 @default.
• W3213441645 creator A5054383195 @default.
• W3213441645 creator A5066907634 @default.
• W3213441645 creator A5072823996 @default.
• W3213441645 creator A5077926417 @default.
• W3213441645 date "2021-09-10" @default.
• W3213441645 modified "2023-09-25" @default.
• W3213441645 title "Topic-Aware Contrastive Learning for Abstractive Dialogue Summarization" @default.
• W3213441645 cites W2054211469 @default.
• W3213441645 cites W2064675550 @default.
• W3213441645 cites W2101390659 @default.
• W3213441645 cites W2154652894 @default.
• W3213441645 cites W2307381258 @default.
• W3213441645 cites W2574535369 @default.
• W3213441645 cites W2606974598 @default.
• W3213441645 cites W2608680710 @default.
• W3213441645 cites W2842511635 @default.
• W3213441645 cites W2888556271 @default.
• W3213441645 cites W2889518897 @default.
• W3213441645 cites W2908336025 @default.
• W3213441645 cites W2912762447 @default.
• W3213441645 cites W2933138175 @default.
• W3213441645 cites W2949530332 @default.
• W3213441645 cites W2951855948 @default.
• W3213441645 cites W2952890017 @default.
• W3213441645 cites W2962785754 @default.
• W3213441645 cites W2962985882 @default.
• W3213441645 cites W2963403868 @default.
• W3213441645 cites W2963545005 @default.
• W3213441645 cites W2964121744 @default.
• W3213441645 cites W2964165364 @default.
• W3213441645 cites W2964308564 @default.
• W3213441645 cites W2970419734 @default.
• W3213441645 cites W2971274815 @default.
• W3213441645 cites W2990953521 @default.
• W3213441645 cites W2996403597 @default.
• W3213441645 cites W3008323921 @default.
• W3213441645 cites W3014468788 @default.
• W3213441645 cites W3021393209 @default.
• W3213441645 cites W3026732421 @default.
• W3213441645 cites W3034715004 @default.
• W3213441645 cites W3034978746 @default.
• W3213441645 cites W3035058308 @default.
• W3213441645 cites W3085629518 @default.
• W3213441645 cites W3098136301 @default.
• W3213441645 cites W3098493824 @default.
• W3213441645 cites W3100345210 @default.
• W3213441645 cites W3104257895 @default.
• W3213441645 cites W3122924117 @default.
• W3213441645 cites W3156636935 @default.
• W3213441645 cites W3169942382 @default.
• W3213441645 cites W2963768805 @default.
• W3213441645 doi "https://doi.org/10.48550/arxiv.2109.04994" @default.
• W3213441645 hasPublicationYear "2021" @default.
• W3213441645 type Work @default.
• W3213441645 sameAs 3213441645 @default.
• W3213441645 citedByCount "0" @default.
• W3213441645 crossrefType "posted-content" @default.
• W3213441645 hasAuthorship W3213441645A5008043408 @default.
• W3213441645 hasAuthorship W3213441645A5041432735 @default.
• W3213441645 hasAuthorship W3213441645A5050030131 @default.
• W3213441645 hasAuthorship W3213441645A5054383195 @default.
• W3213441645 hasAuthorship W3213441645A5066907634 @default.
• W3213441645 hasAuthorship W3213441645A5072823996 @default.
• W3213441645 hasAuthorship W3213441645A5077926417 @default.
• W3213441645 hasBestOaLocation W32134416451 @default.
• W3213441645 hasConcept C121332964 @default.
• W3213441645 hasConcept C13280743 @default.
• W3213441645 hasConcept C138885662 @default.
• W3213441645 hasConcept C148863701 @default.
• W3213441645 hasConcept C154945302 @default.
• W3213441645 hasConcept C161191863 @default.
• W3213441645 hasConcept C162324750 @default.
• W3213441645 hasConcept C170858558 @default.
• W3213441645 hasConcept C185798385 @default.
• W3213441645 hasConcept C187736073 @default.
• W3213441645 hasConcept C204321447 @default.
• W3213441645 hasConcept C205649164 @default.
• W3213441645 hasConcept C23123220 @default.
• W3213441645 hasConcept C26517878 @default.
• W3213441645 hasConcept C2777200299 @default.
• W3213441645 hasConcept C2780451532 @default.
• W3213441645 hasConcept C2780719617 @default.
• W3213441645 hasConcept C2781181686 @default.
• W3213441645 hasConcept C38652104 @default.
• W3213441645 hasConcept C41008148 @default.
• W3213441645 hasConcept C41895202 @default.
• W3213441645 hasConcept C62520636 @default.
• W3213441645 hasConceptScore W3213441645C121332964 @default.
• W3213441645 hasConceptScore W3213441645C13280743 @default.
• W3213441645 hasConceptScore W3213441645C138885662 @default.
• W3213441645 hasConceptScore W3213441645C148863701 @default.
• W3213441645 hasConceptScore W3213441645C154945302 @default.
• W3213441645 hasConceptScore W3213441645C161191863 @default.
• W3213441645 hasConceptScore W3213441645C162324750 @default.
• W3213441645 hasConceptScore W3213441645C170858558 @default.

• next