Abstract: A computer-implemented, machine learning method for generating explainable text summaries includes extracting a subset of sentences from an input document as an extractive summary and adding context to the extracted sentences to generate a prompt. A fluent summary is generated by using the prompt as input to a generative language model. Source information for a sentence from the fluent summary is determined by mapping the sentence from the fluent summary to a sentence in the extractive summary and the sentence from the extractive summary to a sentence from the input document. A transparent summary view is generated showing the sentence from the fluent summary along with the source information from the extractive summary and the input document for display on a user interface. The method has applications including, but not limited to medical AI, public safety and other machine learning applications for reliable and explainable document summarization.

Abstract: To display information providing an insight required by a user, provided is an information processing apparatus (1) including: an obtaining section (11) that obtains an evaluation dataset and context data; a relevance calculation section (12) that calculates a relevance between the context data and a constituent element of the evaluation dataset; an evaluation section (13) that carries out evaluations of a plurality of insight subjects generated with reference to the evaluation dataset and the relevance; and a display section (14) that displays information relevant to the insight subjects.

Abstract: To evaluate whether a visualization candidate of data provides an insight required by a user, an information processing apparatus (1) includes: an obtaining section (11) that obtains an evaluation dataset and context data; and an evaluation section (12) that carries out evaluations of a plurality of insight subjects in relation to the context data, the plurality of insight subjects being generated with reference to at least the evaluation dataset.

Abstract: An information processing device acquires target data, and converts the target data to an embedded vector indicating a latent feature quantity of the target data. Also, the information processing device searches for data similar to the latent feature quantity of the target data as candidate data, and applies a predetermined process to the candidate data to assign a rank to be combined with the target data, for each of the candidate data. Then, the information processing device outputs a result obtained by combining the target data and the candidate data based on the assigned rank.

Abstract: When subscriber(s) have died, a service support apparatus assists in providing service(s) to service recipient(s) registered in advance by subscriber(s) in accordance with subscription content. Subscriber confirmation unit(s) of service support apparatus(es) notify subscriber(s) in the form of message(s) for confirmation of living status, and receive from subscriber(s) reply or replies indicating living status. In the event that there is no reply or replies from subscriber(s), alert unit(s) issue instruction(s) to inquire whether subscriber(s) are dead or alive with collaborator(s) registered in advance by subscriber(s). In the event that it is confirmed that subscriber(s) have died, service instruction unit(s) issue instruction(s) to provide service(s) to service recipient(s). The registration unit is constituted so as to accept registration of service recipient(s) and collaborator(s) by subscriber(s), at which time it is possible to register collaborator(s) by choosing from among service recipient(s).