Matches in SemOpenAlex for { <https://semopenalex.org/work/W2975721763> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2975721763 abstract "Due to the lack of large scale datasets, it remains difficult to train neural Query-focused Multi-Document Summarization (QMDS) models. Several large size datasets on the Document-based Question Answering (DQA) have been released and numerous neural network models achieve good performance. These two tasks above are similar in that they all select sentences from a document to answer a given query/question. We therefore propose a novel adaptation method to improve QMDS by using the relatively large datasets from DQA. Specifically, we first design a neural network model to model both tasks. The model, which consists of a sentence encoder, a query filter and a document encoder, can model the sentence salience and query relevance well. Then we train this model on both the QMDS and DQA datasets with several different strategies. Experimental results on three benchmark DUC datasets demonstrate that our approach outperforms a variety of baselines by a wide margin and achieves comparable results with state-of-the-art methods." @default.
- W2975721763 created "2019-10-03" @default.
- W2975721763 creator A5014662947 @default.
- W2975721763 creator A5017102094 @default.
- W2975721763 creator A5027803148 @default.
- W2975721763 creator A5049732922 @default.
- W2975721763 creator A5077985811 @default.
- W2975721763 date "2019-01-01" @default.
- W2975721763 modified "2023-09-26" @default.
- W2975721763 title "Document-Based Question Answering Improves Query-Focused Multi-document Summarization" @default.
- W2975721763 cites W1902237438 @default.
- W2975721763 cites W1965317094 @default.
- W2975721763 cites W1975061282 @default.
- W2975721763 cites W2052784486 @default.
- W2975721763 cites W2157331557 @default.
- W2975721763 cites W2250361277 @default.
- W2975721763 cites W2250539671 @default.
- W2975721763 cites W2251911042 @default.
- W2975721763 cites W2735674392 @default.
- W2975721763 cites W2888541716 @default.
- W2975721763 cites W2962946054 @default.
- W2975721763 cites W2963538407 @default.
- W2975721763 cites W2963748441 @default.
- W2975721763 cites W3138773240 @default.
- W2975721763 cites W4232339951 @default.
- W2975721763 doi "https://doi.org/10.1007/978-3-030-32236-6_4" @default.
- W2975721763 hasPublicationYear "2019" @default.
- W2975721763 type Work @default.
- W2975721763 sameAs 2975721763 @default.
- W2975721763 citedByCount "0" @default.
- W2975721763 crossrefType "book-chapter" @default.
- W2975721763 hasAuthorship W2975721763A5014662947 @default.
- W2975721763 hasAuthorship W2975721763A5017102094 @default.
- W2975721763 hasAuthorship W2975721763A5027803148 @default.
- W2975721763 hasAuthorship W2975721763A5049732922 @default.
- W2975721763 hasAuthorship W2975721763A5077985811 @default.
- W2975721763 hasConcept C108154423 @default.
- W2975721763 hasConcept C111919701 @default.
- W2975721763 hasConcept C118505674 @default.
- W2975721763 hasConcept C119857082 @default.
- W2975721763 hasConcept C13280743 @default.
- W2975721763 hasConcept C134714966 @default.
- W2975721763 hasConcept C136197465 @default.
- W2975721763 hasConcept C154945302 @default.
- W2975721763 hasConcept C158154518 @default.
- W2975721763 hasConcept C170858558 @default.
- W2975721763 hasConcept C17744445 @default.
- W2975721763 hasConcept C185798385 @default.
- W2975721763 hasConcept C199539241 @default.
- W2975721763 hasConcept C205649164 @default.
- W2975721763 hasConcept C23123220 @default.
- W2975721763 hasConcept C2777530160 @default.
- W2975721763 hasConcept C41008148 @default.
- W2975721763 hasConcept C44291984 @default.
- W2975721763 hasConcept C774472 @default.
- W2975721763 hasConcept C99016210 @default.
- W2975721763 hasConceptScore W2975721763C108154423 @default.
- W2975721763 hasConceptScore W2975721763C111919701 @default.
- W2975721763 hasConceptScore W2975721763C118505674 @default.
- W2975721763 hasConceptScore W2975721763C119857082 @default.
- W2975721763 hasConceptScore W2975721763C13280743 @default.
- W2975721763 hasConceptScore W2975721763C134714966 @default.
- W2975721763 hasConceptScore W2975721763C136197465 @default.
- W2975721763 hasConceptScore W2975721763C154945302 @default.
- W2975721763 hasConceptScore W2975721763C158154518 @default.
- W2975721763 hasConceptScore W2975721763C170858558 @default.
- W2975721763 hasConceptScore W2975721763C17744445 @default.
- W2975721763 hasConceptScore W2975721763C185798385 @default.
- W2975721763 hasConceptScore W2975721763C199539241 @default.
- W2975721763 hasConceptScore W2975721763C205649164 @default.
- W2975721763 hasConceptScore W2975721763C23123220 @default.
- W2975721763 hasConceptScore W2975721763C2777530160 @default.
- W2975721763 hasConceptScore W2975721763C41008148 @default.
- W2975721763 hasConceptScore W2975721763C44291984 @default.
- W2975721763 hasConceptScore W2975721763C774472 @default.
- W2975721763 hasConceptScore W2975721763C99016210 @default.
- W2975721763 hasLocation W29757217631 @default.
- W2975721763 hasOpenAccess W2975721763 @default.
- W2975721763 hasPrimaryLocation W29757217631 @default.
- W2975721763 hasRelatedWork W11133913 @default.
- W2975721763 hasRelatedWork W2060686 @default.
- W2975721763 hasRelatedWork W2371595 @default.
- W2975721763 hasRelatedWork W3901497 @default.
- W2975721763 hasRelatedWork W4742464 @default.
- W2975721763 hasRelatedWork W4867410 @default.
- W2975721763 hasRelatedWork W5977128 @default.
- W2975721763 hasRelatedWork W6264993 @default.
- W2975721763 hasRelatedWork W803423 @default.
- W2975721763 hasRelatedWork W9077160 @default.
- W2975721763 isParatext "false" @default.
- W2975721763 isRetracted "false" @default.
- W2975721763 magId "2975721763" @default.
- W2975721763 workType "book-chapter" @default.