首页|Recent Research from University of Innsbruck Highlight Findings in Machine Learn ing (Temporal Validity Reassessment: Commonsense Reasoning About Information Obs oleteness)
Recent Research from University of Innsbruck Highlight Findings in Machine Learn ing (Temporal Validity Reassessment: Commonsense Reasoning About Information Obs oleteness)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting originating in Innsbruck, A ustria, by NewsRx journalists, research stated, "It is useful for machines to kn ow whether text information remains valid or not for various applications includ ing text comprehension, story understanding, temporal information retrieval, and user state tracking on microblogs as well as via chatbot conversations. This ki nd of inference is still difficult for current models, including also large lang uage models, as it requires temporal commonsense knowledge and reasoning." Financial support for this research came from University of Innsbruck and Medica l University of Innsbruck. The news reporters obtained a quote from the research from the University of Inn sbruck, "We approach in this paper the task of Temporal Validity Reassessment, i nspired by traditional natural language reasoning to determine the updates of th e temporal validity of text content. The task requires judgment whether actions expressed in a sentence are still ongoing or rather completed, hence, whether th e sentence still remains valid or has become obsolete, given the presence of con text in the form of a supplementary content such as a follow-up sentence. We fir st construct our own dataset for this task and train several machine learning mo dels. Then we propose an effective method for learning information from an exter nal knowledge base that gives information regarding temporal commonsense knowled ge. Using our prepared dataset, we introduce a machine learning model that incor porates the information from the knowledge base and demonstrate that incorporati ng external knowledge generally improves the results."
InnsbruckAustriaEuropeCyborgsEme rging TechnologiesMachine LearningUniversity of Innsbruck
NETL
NSTL
