FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3124392492> ?p ?o ?g. }

• W3124392492 abstract "With the development of deep learning techniques and large scale datasets, the question answering (QA) systems have been quickly improved, providing more accurate and satisfying answers. However, current QA systems either focus on the sentence-level answer, i.e., answer selection, or phrase-level answer, i.e., machine reading comprehension. How to produce compositional answers has not been throughout investigated. In compositional question answering, the systems should assemble several supporting evidence from the document to generate the final answer, which is more difficult than sentence-level or phrase-level QA. In this paper, we present a large-scale compositional question answering dataset containing more than 120k human-labeled questions. The answer in this dataset is composed of discontiguous sentences in the corresponding document. To tackle the ComQA problem, we proposed a hierarchical graph neural networks, which represents the document from the low-level word to the high-level sentence. We also devise a question selection and node selection task for pre-training. Our proposed model achieves a significant improvement over previous machine reading comprehension methods and pre-training methods. Codes and dataset can be found at url{https://github.com/benywon/ComQA}." @default.
• W3124392492 created "2021-02-01" @default.
• W3124392492 creator A5024810143 @default.
• W3124392492 creator A5037383078 @default.
• W3124392492 creator A5056336684 @default.
• W3124392492 creator A5081143722 @default.
• W3124392492 creator A5088760097 @default.
• W3124392492 date "2021-01-16" @default.
• W3124392492 modified "2023-09-26" @default.
• W3124392492 title "ComQA:Compositional Question Answering via Hierarchical Graph Neural Networks" @default.
• W3124392492 cites W1554944419 @default.
• W3124392492 cites W1979263599 @default.
• W3124392492 cites W2016381774 @default.
• W3124392492 cites W2095705004 @default.
• W3124392492 cites W2097123411 @default.
• W3124392492 cites W2125436846 @default.
• W3124392492 cites W2131965512 @default.
• W3124392492 cites W2135514656 @default.
• W3124392492 cites W2427527485 @default.
• W3124392492 cites W2551396370 @default.
• W3124392492 cites W2786864293 @default.
• W3124392492 cites W2805516822 @default.
• W3124392492 cites W2885185669 @default.
• W3124392492 cites W2892094955 @default.
• W3124392492 cites W2896457183 @default.
• W3124392492 cites W2899663614 @default.
• W3124392492 cites W2908510526 @default.
• W3124392492 cites W2912924812 @default.
• W3124392492 cites W2919420119 @default.
• W3124392492 cites W2949615363 @default.
• W3124392492 cites W2951534261 @default.
• W3124392492 cites W2952862139 @default.
• W3124392492 cites W2953359159 @default.
• W3124392492 cites W2962784628 @default.
• W3124392492 cites W2962946486 @default.
• W3124392492 cites W2963403868 @default.
• W3124392492 cites W2963460103 @default.
• W3124392492 cites W2963564796 @default.
• W3124392492 cites W2963625095 @default.
• W3124392492 cites W2963858333 @default.
• W3124392492 cites W2963866616 @default.
• W3124392492 cites W2964121744 @default.
• W3124392492 cites W2964298608 @default.
• W3124392492 cites W2965373594 @default.
• W3124392492 cites W2970597249 @default.
• W3124392492 cites W2970971581 @default.
• W3124392492 cites W2997354568 @default.
• W3124392492 cites W2998369048 @default.
• W3124392492 cites W3008686018 @default.
• W3124392492 cites W3036216033 @default.
• W3124392492 cites W3045733172 @default.
• W3124392492 cites W3084791644 @default.
• W3124392492 doi "https://doi.org/10.48550/arxiv.2101.06400" @default.
• W3124392492 hasPublicationYear "2021" @default.
• W3124392492 type Work @default.
• W3124392492 sameAs 3124392492 @default.
• W3124392492 citedByCount "0" @default.
• W3124392492 crossrefType "posted-content" @default.
• W3124392492 hasAuthorship W3124392492A5024810143 @default.
• W3124392492 hasAuthorship W3124392492A5037383078 @default.
• W3124392492 hasAuthorship W3124392492A5056336684 @default.
• W3124392492 hasAuthorship W3124392492A5081143722 @default.
• W3124392492 hasAuthorship W3124392492A5088760097 @default.
• W3124392492 hasBestOaLocation W31243924921 @default.
• W3124392492 hasConcept C132525143 @default.
• W3124392492 hasConcept C154945302 @default.
• W3124392492 hasConcept C199360897 @default.
• W3124392492 hasConcept C204321447 @default.
• W3124392492 hasConcept C23123220 @default.
• W3124392492 hasConcept C2776224158 @default.
• W3124392492 hasConcept C2777530160 @default.
• W3124392492 hasConcept C41008148 @default.
• W3124392492 hasConcept C44291984 @default.
• W3124392492 hasConcept C511192102 @default.
• W3124392492 hasConcept C80444323 @default.
• W3124392492 hasConcept C81917197 @default.
• W3124392492 hasConceptScore W3124392492C132525143 @default.
• W3124392492 hasConceptScore W3124392492C154945302 @default.
• W3124392492 hasConceptScore W3124392492C199360897 @default.
• W3124392492 hasConceptScore W3124392492C204321447 @default.
• W3124392492 hasConceptScore W3124392492C23123220 @default.
• W3124392492 hasConceptScore W3124392492C2776224158 @default.
• W3124392492 hasConceptScore W3124392492C2777530160 @default.
• W3124392492 hasConceptScore W3124392492C41008148 @default.
• W3124392492 hasConceptScore W3124392492C44291984 @default.
• W3124392492 hasConceptScore W3124392492C511192102 @default.
• W3124392492 hasConceptScore W3124392492C80444323 @default.
• W3124392492 hasConceptScore W3124392492C81917197 @default.
• W3124392492 hasLocation W31243924921 @default.
• W3124392492 hasOpenAccess W3124392492 @default.
• W3124392492 hasPrimaryLocation W31243924921 @default.
• W3124392492 hasRelatedWork W128392744 @default.
• W3124392492 hasRelatedWork W1517743118 @default.
• W3124392492 hasRelatedWork W1556931475 @default.
• W3124392492 hasRelatedWork W159132833 @default.
• W3124392492 hasRelatedWork W20999564 @default.
• W3124392492 hasRelatedWork W2251181482 @default.
• W3124392492 hasRelatedWork W2398825887 @default.
• W3124392492 hasRelatedWork W2411652523 @default.
• W3124392492 hasRelatedWork W3162043819 @default.

• next