Abstract: In one embodiment, a system includes an automatic speech recognition (ASR) module, a natural-language understanding (NLU) module, a dialog manager, one or more agents, an arbitrator, a delivery system, one or more processors, and a non-transitory memory coupled to the processors comprising instructions executable by the processors, the processors operable when executing the instructions to receive a user input, process the user input using the ASR module, the NLU module, the dialog manager, one or more of the agents, the arbitrator, and the delivery system, and provide a response to the user input.

Abstract: An online system maintains a web page associated with one or more page administrators. The online system trains a machine learning model to determine a likelihood of a page administrator account accepting a request for the online system to present content about the web page to other users of the online system. The model uses features extracted from data about the page administrator accounts on the online system, the page administrator interactions with the online system, and the web page. The online system selects one or more page administrator accounts and sends them requests based on the determined likelihood scores. The online system delivers content associated with the web page to users of the online system based on a response to the request.

Abstract: An online system maintains a web page associated with one or more page administrators. The online system trains a machine learning model to determine a likelihood of a page administrator account accepting a request for the online system to present content about the web page to other users of the online system. The model uses features extracted from data about the page administrator accounts on the online system, the page administrator interactions with the online system, and the web page. The online system selects one or more page administrator accounts and sends them requests based on the determined likelihood scores. The online system delivers content associated with the web page to users of the online system based on a response to the request.

Abstract: Systems, methods, and non-transitory computer readable media can obtain a plurality of calls-to-action (CTAs) that can be provided on a page associated with a social networking system. A machine learning model can be trained based on training data including pages and associated CTAs. The plurality of CTAs for a page can be ranked based on the machine learning model. At least one of the ranked CTAs for the page can be provided as a recommended CTA for the page.

Abstract: A online system generates and displays page promotion units to viewing users of the online system. The page promotion unit provides content to the viewing user to promote advertisement of a page that the viewing user administers or advertises for. The page promotion unit may be dynamically generated based on content of the page that the viewing user administers. The page promotion unit may also include suggested operational parameters for a campaign to display the content, which may include budget or suggested targeting criteria, as well as estimated reach for the campaign. The page promotion unit also provides an interface for the viewing user to promote the page and direct the viewing user to an interface for initiating an advertising campaign for the page, which may be prepopulated with content from the page promotion unit.

Abstract: An online system maintains a web page associated with one or more page administrators. The online system trains a machine learning model to determine a likelihood of a page administrator account accepting a request for the online system to present content about the web page to other users of the online system. The model uses features extracted from data about the page administrator accounts on the online system, the page administrator interactions with the online system, and the web page. The online system selects one or more page administrator accounts and sends them requests based on the determined likelihood scores. The online system delivers content associated with the web page to users of the online system based on a response to the request.