Matches in SemOpenAlex for { <https://semopenalex.org/work/W2015290450> ?p ?o ?g. }
Showing items 1 to 66 of
66
with 100 items per page.
- W2015290450 abstract "Despite the success of large knowledge bases, one kind of knowledge that has not received attention so far is that of human activities. An example of such an activity is proposing to someone (to get married). For the computer, knowing that this involves two adults, often but not necessarily a woman and a man, that it often takes place in some romantic location, that it typically involves flowers or jewelry, and that it is usually followed by kissing, is a valuable asset for tasks like natural language dialog, scene understanding, or video search. This corresponds to the challenging task of acquiring semantic frames that capture human activities, their participating agents, and their typical spatio-temporal contexts. This paper presents a novel approach that taps into movie scripts and other narrative texts. We develop a pipeline for semantic parsing and knowledge distillation, to systematically compile semantically refined activity frames. The resulting knowledge base contains hundreds of thousands of activity frames, mined from about two million scenes of movies, TV series, and novels. A manual assessment study, with extensive sampling and statistical significance tests, shows that the frames and their attribute values have an accuracy of at least 80 percent. We also demonstrate the usefulness of activity knowledge by the extrinsic use case of movie scene search." @default.
- W2015290450 created "2016-06-24" @default.
- W2015290450 creator A5026269420 @default.
- W2015290450 creator A5052882677 @default.
- W2015290450 creator A5085818578 @default.
- W2015290450 creator A5088135366 @default.
- W2015290450 date "2015-10-17" @default.
- W2015290450 modified "2023-09-23" @default.
- W2015290450 title "Knowlywood" @default.
- W2015290450 cites W1529731474 @default.
- W2015290450 cites W1641039719 @default.
- W2015290450 cites W1964763677 @default.
- W2015290450 cites W1965605789 @default.
- W2015290450 cites W1971217926 @default.
- W2015290450 cites W2019660985 @default.
- W2015290450 cites W2022166150 @default.
- W2015290450 cites W2051398498 @default.
- W2015290450 cites W2075123415 @default.
- W2015290450 cites W2083897630 @default.
- W2015290450 cites W2090243146 @default.
- W2015290450 cites W2094728533 @default.
- W2015290450 cites W2106578604 @default.
- W2015290450 cites W2111078031 @default.
- W2015290450 cites W2147923392 @default.
- W2015290450 cites W2151170651 @default.
- W2015290450 cites W2151386575 @default.
- W2015290450 cites W2158847908 @default.
- W2015290450 cites W2252215150 @default.
- W2015290450 cites W2436001372 @default.
- W2015290450 doi "https://doi.org/10.1145/2806416.2806583" @default.
- W2015290450 hasPublicationYear "2015" @default.
- W2015290450 type Work @default.
- W2015290450 sameAs 2015290450 @default.
- W2015290450 citedByCount "40" @default.
- W2015290450 countsByYear W20152904502015 @default.
- W2015290450 countsByYear W20152904502016 @default.
- W2015290450 countsByYear W20152904502017 @default.
- W2015290450 countsByYear W20152904502018 @default.
- W2015290450 countsByYear W20152904502019 @default.
- W2015290450 countsByYear W20152904502020 @default.
- W2015290450 countsByYear W20152904502021 @default.
- W2015290450 countsByYear W20152904502022 @default.
- W2015290450 crossrefType "proceedings-article" @default.
- W2015290450 hasAuthorship W2015290450A5026269420 @default.
- W2015290450 hasAuthorship W2015290450A5052882677 @default.
- W2015290450 hasAuthorship W2015290450A5085818578 @default.
- W2015290450 hasAuthorship W2015290450A5088135366 @default.
- W2015290450 hasConcept C41008148 @default.
- W2015290450 hasConceptScore W2015290450C41008148 @default.
- W2015290450 hasLocation W20152904501 @default.
- W2015290450 hasOpenAccess W2015290450 @default.
- W2015290450 hasPrimaryLocation W20152904501 @default.
- W2015290450 hasRelatedWork W2049775471 @default.
- W2015290450 hasRelatedWork W2093578348 @default.
- W2015290450 hasRelatedWork W2350741829 @default.
- W2015290450 hasRelatedWork W2358668433 @default.
- W2015290450 hasRelatedWork W2376932109 @default.
- W2015290450 hasRelatedWork W2382290278 @default.
- W2015290450 hasRelatedWork W2390279801 @default.
- W2015290450 hasRelatedWork W2748952813 @default.
- W2015290450 hasRelatedWork W2899084033 @default.
- W2015290450 hasRelatedWork W3004735627 @default.
- W2015290450 isParatext "false" @default.
- W2015290450 isRetracted "false" @default.
- W2015290450 magId "2015290450" @default.
- W2015290450 workType "article" @default.