Abstract: An embedding associated with a query comprising one or more query terms is determined to be not stored in memory. An embedding is generated for the one or more query terms. One or more web documents that are similar to the generated embedding are determined. One or more content cards associated with the one or more web documents that are determined to be similar to the generated embedding are provided in a content feed.

Abstract: Techniques for generating interest embedding vectors are disclosed. In some embodiments, a system/process/computer program product for generating interest embedding vectors includes aggregating a plurality of web documents associated with one or more entities, wherein the web documents are retrieved from a plurality of online content sources including one or more websites; selecting a plurality of tokens based on processing of the plurality of web documents; and generating embeddings of the selected tokens in an embedding space.

Abstract: A set of documents associated with a query comprising one or more query terms is determined. A subset of the documents is sampled to identify a corresponding query constraint pattern associated with each document included in the subset of the documents. An entry of an inverted index is generated based on the corresponding query constraint pattern associated with each document included in the subset of document.

Abstract: A set of documents associated with a query comprising one or more query terms is determined. A subset of the documents is sampled to identify a corresponding query constraint pattern associated with each document included in the subset of the documents. An entry of an inverted index is generated based on the corresponding query constraint pattern associated with each document included in the subset of document.

Abstract: One or more trending subtopics associated with a topic included in a query are determined. A selection of the one or more trending subtopics is received. One or more web documents associated with the selected trending subtopic are provided.

Abstract: One or more content examples associated with a content channel are received. One or more entities are determined based on the one or more content examples. One or more web documents are provided in a content feed based on the one or more determined entities.

Abstract: A query that includes an entity is received. One or more entities from a plurality of entities that are similar to the entity included in the query are determined based on a sim hash associated with the entity included in the query and one or more corresponding sim hashes associated with the one or more entities. The sim hash associated with the entity included in the query and the corresponding sim hashes associated with the entity are based on a plurality of random hyperplanes. A content feed is updated based on the determined one or more entities.

Abstract: A nearest neighbor image embedding associated with an n-gram is determined. The nearest neighbor image embedding is associated with an image. One or more web documents associated with the n-gram and the image are provided in a content feed.

Abstract: Techniques for generating interest embedding vectors are disclosed. In some embodiments, a system/process/computer program product for generating interest embedding vectors includes aggregating a plurality of web documents associated with one or more entities, wherein the web documents are retrieved from a plurality of online content sources including one or more websites; selecting a plurality of tokens based on processing of the plurality of web documents; and generating embeddings of the selected tokens in an embedding space.

Abstract: Techniques for generating an index for enhanced search based on user interests are disclosed. In some embodiments, a system/process/computer program product for generating an index for enhanced search based on user interests includes aggregating a plurality of web documents associated with one or more entities, wherein the web documents are retrieved from a plurality of online content sources including websites; determining relationships between each of the plurality of web documents, wherein the relationships include online relationships; and generating an index that includes the plurality of web documents and the relationships between each of the plurality of web documents.

Abstract: Techniques for providing an enhanced search to generate a feed based on a user's interests are disclosed. In some embodiments, a system/process/computer program product for providing an enhanced search to generate a feed based on a user's interests includes receiving a plurality of interests associated with a user, searching online content including one or more websites (e.g., news or other content websites, social networking sites, and/or other online content) based on the plurality of interests associated with the user, receiving a plurality of web documents (e.g., links to websites, social networking sites, and other online content) based on the search for online content, ranking the plurality of web documents based on a document score and a user signal, and generating a content feed that includes at least a subset of the plurality of web documents based on the ranking.

Abstract: Techniques for providing user interest modeling are disclosed. In some embodiments, a system/process/computer program product for providing user interest modeling includes determining a plurality of interests associated with a user account and generated a content feed for a user that includes one or more web documents based on the plurality of interests.

Abstract: Techniques for enhanced search for generating a content feed are disclosed. In some embodiments, a system/process/computer program product for enhanced search for generating a content feed includes determining a plurality of interests for a user, wherein the user is associated with a user account; searching one or more websites based on the plurality of interests associated with the user; generating an index that includes a plurality of web documents and relationships between each of the plurality of web documents; and generating a content feed that includes at least a subset of the plurality of web documents based on a ranking, wherein the ranking is based on the plurality of interests associated with the user.