Abstract: In one embodiment, a method includes accessing a place-entities graph comprising a plurality of place-entity nodes, in which each place-entity node representing a place-entity corresponding to a particular geographic location, and identifying a place-entity cluster within the place-entities graph. The place-entity cluster comprises a plurality of place-entity nodes corresponding to a plurality of place-entities corresponding to the same geographic location. The method includes accessing embeddings representing the plurality of place-entities corresponding to the place-entity cluster. Each embedding is a point in a d-dimensional embedding space. The method includes calculating, using a machine-learning model, a cluster-quality score of the place-entity cluster based on the embeddings. The cluster-quality score represents a probability that the place-entities correspond to a valid geographic location.

Abstract: In one embodiment, a method includes receiving, from a client system associated with a user of an online social network, data indicating that the user is located at a first geographic location at a first time; accessing a first embedding representing a first place-entity corresponding to the first geographic location; accessing multiple second embeddings representing multiple respective second place-entities each corresponding to a second geographic location; calculating, a similarity metric between the embedding representing the first place-entity and each of the embeddings representing the second place-entities; ranking each of the second place-entities based on their calculated similarity metrics; and sending, to the client system, information associated with one or more second geographic locations corresponding to one or more second place-entities having a ranking greater than a threshold ranking.

Abstract: In one embodiment, a method includes receiving, from a client system, a search query, identifying a plurality of place-entity nodes matching the search query, determining that one or more of the identified place-entity nodes are low-quality place-entity nodes based on the place names of the place-entity nodes having anomalous language characteristics, filtering the plurality of identified place-entity nodes to exclude the determined low-quality place-entity nodes, and generating one or more search results corresponding to the plurality of filtered place-entity nodes.

Abstract: In one embodiment, a method includes receiving from a client system a search query, identifying a first place-entity based on the search query, accessing a place-entities graph comprising a plurality of place-entity nodes, each place-entity node representing a particular place-entity associated with a particular geographic location, wherein the first place-entity is represented by a first place-entity node, accessing a redirection graph comprising the plurality of place-entity nodes and a plurality of place-entity clusters, each place-entity node in a place-entity cluster having a redirection edge connecting the place-entity node to a canonical place-entity node of the respective place-entity cluster, and sending a response to the search query, wherein if the first place-entity node is connected to a canonical place-entity node by a redirection edge within the redirection graph, the response comprises a reference to the canonical place-entity node, else the response comprises a reference to the first place-en

Abstract: In one embodiment, an online social network accesses a place-entity cluster comprising a number of place-entity nodes corresponding to a particular place-entity having a geographic location. One of the place-entity nodes is identified as an initial canonical place-entity cluster connected to the other place-entity nodes by redirection edges. A cluster score is calculated for each place-entity node in the cluster, and nodes having a cluster score above a threshold is identified. One of the identified place-entity nodes is selected as a replacement canonical place-entity node. If the replacement node is different from the initial canonical node, then the place-entity cluster is updated by adding or removing at least one place-entity node from the cluster based on their respective cluster scores.

Abstract: In one embodiment, a method includes receiving from a client system a search query, identifying a first place-entity based on the search query, accessing a place-entities graph comprising a plurality of place-entity nodes, each place-entity node representing a particular place-entity associated with a particular geographic location, wherein the first place-entity is represented by a first place-entity node, accessing a redirection graph comprising the plurality of place-entity nodes and a plurality of place-entity clusters, each place-entity node in a place-entity cluster having a redirection edge connecting the place-entity node to a canonical place-entity node of the respective place-entity cluster, and sending a response to the search query, wherein if the first place-entity node is connected to a canonical place-entity node by a redirection edge within the redirection graph, the response comprises a reference to the canonical place-entity node, else the response comprises a reference to the first place-en

Abstract: In one embodiment, a method includes receiving, from a client system associated with a user of an online social network, data indicating that the user is located at a first geographic location at a first time; accessing a first embedding representing a first place-entity corresponding to the first geographic location; accessing multiple second embeddings representing multiple respective second place-entities each corresponding to a second geographic location; calculating, a similarity metric between the embedding representing the first place-entity and each of the embeddings representing the second place-entities; ranking each of the second place-entities based on their calculated similarity metrics; and sending, to the client system, information associated with one or more second geographic locations corresponding to one or more second place-entities having a ranking greater than a threshold ranking.

Abstract: In one embodiment, an online social network accesses a place-entities graph that includes a plurality of place-entity nodes, each place-entity node representing a particular place-entity associated with a particular geographic location. From one of a plurality of search clients associated with the online social network, a threshold duplication value and a threshold redirect value is received. The online social network identifies place-entity clusters of place-entity nodes within the place-entities graph. In each place-entity cluster, the place-entity nodes have duplication values with respect to a canonical place-entity node in the cluster that are above the threshold duplication value. The online social network generates a redirection graph for the one search client.

Abstract: In one embodiment, an online social network accesses a place-entity cluster comprising a number of place-entity nodes corresponding to a particular place-entity having a geographic location. One of the place-entity nodes is identified as an initial canonical place-entity cluster connected to the other place-entity nodes by redirection edges. A cluster score is calculated for each place-entity node in the cluster, and nodes having a cluster score above a threshold is identified. One of the identified place-entity nodes is selected as a replacement canonical place-entity node. If the replacement node is different from the initial canonical node, then the place-entity cluster is updated by adding or removing at least one place-entity node from the cluster based on their respective cluster scores.

Abstract: In one embodiment, an online social network accesses a place-entities graph that includes a plurality of place-entity nodes, each place-entity node representing a particular place-entity associated with a particular geographic location. From one of a plurality of search clients associated with the online social network, a threshold duplication value and a threshold redirect value is received. The online social network identifies place-entity clusters of place-entity nodes within the place-entities graph. In each place-entity cluster, the place-entity nodes have duplication values with respect to a canonical place-entity node in the cluster that are above the threshold duplication value. The online social network generates a redirection graph for the one search client.