Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204602149> ?p ?o ?g. }
- W3204602149 endingPage "1116" @default.
- W3204602149 startingPage "1106" @default.
- W3204602149 abstract "Table2Text systems generate textual output based on structured data utilizing machine learning. These systems are essential for fluent natural language interfaces in tools such as virtual assistants; however, left to generate freely these ML systems often produce misleading or unexpected outputs. GenNI (Generation Negotiation Interface) is an interactive visual system for high-level human-AI collaboration in producing descriptive text. The tool utilizes a deep learning model designed with explicit control states. These controls allow users to globally constrain model generations, without sacrificing the representation power of the deep learning models. The visual interface makes it possible for users to interact with AI systems following a Refine-Forecast paradigm to ensure that the generation system acts in a manner human users find suitable. We report multiple use cases on two experiments that improve over uncontrolled generation approaches, while at the same time providing fine-grained control. A demo and source code are available at https://genni.vizhub.ai." @default.
- W3204602149 created "2021-10-11" @default.
- W3204602149 creator A5007955515 @default.
- W3204602149 creator A5010238198 @default.
- W3204602149 creator A5043151044 @default.
- W3204602149 creator A5083754593 @default.
- W3204602149 creator A5084459196 @default.
- W3204602149 creator A5086644493 @default.
- W3204602149 date "2022-01-01" @default.
- W3204602149 modified "2023-09-26" @default.
- W3204602149 title "GenNI: Human-AI Collaboration for Data-Backed Text Generation" @default.
- W3204602149 cites W1985610876 @default.
- W3204602149 cites W2058043539 @default.
- W3204602149 cites W2082118847 @default.
- W3204602149 cites W2106087324 @default.
- W3204602149 cites W2125394509 @default.
- W3204602149 cites W2739046565 @default.
- W3204602149 cites W2752194699 @default.
- W3204602149 cites W2889009749 @default.
- W3204602149 cites W2891963134 @default.
- W3204602149 cites W2891999054 @default.
- W3204602149 cites W2903156194 @default.
- W3204602149 cites W2924992615 @default.
- W3204602149 cites W2947683321 @default.
- W3204602149 cites W2950784811 @default.
- W3204602149 cites W2951080837 @default.
- W3204602149 cites W2953147883 @default.
- W3204602149 cites W2962905474 @default.
- W3204602149 cites W2963018534 @default.
- W3204602149 cites W2963091658 @default.
- W3204602149 cites W2963123635 @default.
- W3204602149 cites W2963126845 @default.
- W3204602149 cites W2963214037 @default.
- W3204602149 cites W2963912046 @default.
- W3204602149 cites W2964200170 @default.
- W3204602149 cites W2969282568 @default.
- W3204602149 cites W2973221207 @default.
- W3204602149 cites W3034476403 @default.
- W3204602149 cites W3034948406 @default.
- W3204602149 cites W3035140194 @default.
- W3204602149 cites W3037738964 @default.
- W3204602149 cites W3037969532 @default.
- W3204602149 cites W3038035611 @default.
- W3204602149 cites W3101819830 @default.
- W3204602149 cites W3124386704 @default.
- W3204602149 cites W4292763141 @default.
- W3204602149 doi "https://doi.org/10.1109/tvcg.2021.3114845" @default.
- W3204602149 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34587072" @default.
- W3204602149 hasPublicationYear "2022" @default.
- W3204602149 type Work @default.
- W3204602149 sameAs 3204602149 @default.
- W3204602149 citedByCount "3" @default.
- W3204602149 countsByYear W32046021492022 @default.
- W3204602149 crossrefType "journal-article" @default.
- W3204602149 hasAuthorship W3204602149A5007955515 @default.
- W3204602149 hasAuthorship W3204602149A5010238198 @default.
- W3204602149 hasAuthorship W3204602149A5043151044 @default.
- W3204602149 hasAuthorship W3204602149A5083754593 @default.
- W3204602149 hasAuthorship W3204602149A5084459196 @default.
- W3204602149 hasAuthorship W3204602149A5086644493 @default.
- W3204602149 hasBestOaLocation W32046021492 @default.
- W3204602149 hasConcept C107457646 @default.
- W3204602149 hasConcept C108583219 @default.
- W3204602149 hasConcept C111919701 @default.
- W3204602149 hasConcept C113843644 @default.
- W3204602149 hasConcept C119857082 @default.
- W3204602149 hasConcept C129307140 @default.
- W3204602149 hasConcept C154945302 @default.
- W3204602149 hasConcept C157915830 @default.
- W3204602149 hasConcept C177264268 @default.
- W3204602149 hasConcept C17744445 @default.
- W3204602149 hasConcept C199360897 @default.
- W3204602149 hasConcept C199539241 @default.
- W3204602149 hasConcept C2775924081 @default.
- W3204602149 hasConcept C2776359362 @default.
- W3204602149 hasConcept C2776760102 @default.
- W3204602149 hasConcept C2985684807 @default.
- W3204602149 hasConcept C41008148 @default.
- W3204602149 hasConcept C43126263 @default.
- W3204602149 hasConcept C89505385 @default.
- W3204602149 hasConcept C94625758 @default.
- W3204602149 hasConceptScore W3204602149C107457646 @default.
- W3204602149 hasConceptScore W3204602149C108583219 @default.
- W3204602149 hasConceptScore W3204602149C111919701 @default.
- W3204602149 hasConceptScore W3204602149C113843644 @default.
- W3204602149 hasConceptScore W3204602149C119857082 @default.
- W3204602149 hasConceptScore W3204602149C129307140 @default.
- W3204602149 hasConceptScore W3204602149C154945302 @default.
- W3204602149 hasConceptScore W3204602149C157915830 @default.
- W3204602149 hasConceptScore W3204602149C177264268 @default.
- W3204602149 hasConceptScore W3204602149C17744445 @default.
- W3204602149 hasConceptScore W3204602149C199360897 @default.
- W3204602149 hasConceptScore W3204602149C199539241 @default.
- W3204602149 hasConceptScore W3204602149C2775924081 @default.
- W3204602149 hasConceptScore W3204602149C2776359362 @default.
- W3204602149 hasConceptScore W3204602149C2776760102 @default.
- W3204602149 hasConceptScore W3204602149C2985684807 @default.
- W3204602149 hasConceptScore W3204602149C41008148 @default.