Abstract: Systems and methods are provided for learning classifiers for annotating a document with predicted labels under extreme classification where there are over a million labels. The learning includes receiving a joint graph including documents and labels as nodes. Multi-dimensional vector representations of a document (i.e., document representations) are generated based on graph convolution of the joint graph. Each document representation varies an extent of reliance on neighboring nodes to accommodate context. The document representations are feature-transformed using a residual layer. Per-label document representations are generated from the transformed document representations based on neighboring label attention. A classifier is trained for each of over a million labels based on joint learning using training data and the per-label document representation. The trained classifier performs highly efficiently as compared to other classifiers trained using disjoint graphs of documents and labels.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A computer-implemented method can include receiving, in a system that maintains web notebooks for a plurality of user accounts, a request for a web document from a client computing device; determining whether a portion of the requested web document is included in a web notebook associated with one of the plurality of user accounts; and when it is determined that the portion is included in a web notebook associated with one of the plurality of user accounts, providing for display by the client computing device a highlighted version of the web document having a visual indicator that highlights the portion. Determining whether a portion of the requested web document is included in a web notebook associated with one of the plurality of user accounts can include determining whether the portion is included in at least a threshold number of web notebooks associated with distinct user accounts.

Abstract: A device identifies a search result document based on a search query, and searches a blog post repository to identify a blog post relevant to the search result document. The device also rejects the blog post if the blog post has insufficient length, contains outgoing links located a predetermined distance from the beginning of the blog post, has a large out-degree, was created before or after a predetermined time, or has incoming links with a low link-based score. The device further provides the blog post in connection with the search result document if the blog post was not rejected.

Abstract: Systems and methods for providing refinements to queries based upon the context of a refinement indication. Refinements, for example, can be related to a previous search query and can be provided to the user based upon receipt of a refinement indication.

Abstract: A computer-implemented method of providing information for a web notebook is disclosed. The method can include displaying a web document in a content area of a browser window, receiving a user selection of content from the document initiated by a first user mouse click, and displaying a selection icon in the content area upon completion of the user selection, wherein the selection icon is displayed without the need for a second user mouse click.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for searching a data set and returning search results organized in a hierarchy of categories are disclosed. A set of categories is provided for organizing a set of search results, wherein each category is associated with one or more search results. The set of search results is organized into a hierarchy of categories, the hierarchy including at least one category from the set of categories. At least a portion of the hierarchy of categories is displayed and a user request to modify the hierarchy of categories is received. The hierarchy of categories is modified in accordance with the user request.

Abstract: A device identifies a search result document based on a search query, and searches a blog post repository to identify a blog post relevant to the search result document. The device also rejects the blog post if the blog post has insufficient length, contains outgoing links located a predetermined distance from the beginning of the blog post, has a large out-degree, was created before or after a predetermined time, or has incoming links with a low link-based score. The device further provides the blog post in connection with the search result document if the blog post was not rejected.

Abstract: Systems and methods for providing refinements to queries based upon the context of a refinement indication. Refinements, for example, can be related to a previous search query and can be provided to the user based upon receipt of a refinement indication.

Abstract: A computer-implemented method of providing information for a web notebook is disclosed. The method can include displaying a web document in a content area of a browser window, receiving a user selection of content from the document initiated by a first user mouse click, and displaying a selection icon in the content area upon completion of the user selection, wherein the selection icon is displayed without the need for a second user mouse click.

Abstract: A method of presenting computer-generated search result information can include receiving a search request from a client computer; identifying a plurality of search results responsive to the search request; ranking the plurality of search results using content in one or more web notebooks; and providing the ranked plurality of search results for presentation in the client computer. Using the content can include determining whether at least one of a title, a heading, clipped content, metadata or a user-annotation in at least one web notebook relates to the search request and, if so, increasing a ranking of at least one search result referenced by the at least one web notebook.

Abstract: A method and system of selecting content from reviews for display are described. A review is identified and partitioned. A subset of the partitions is selected based on predefined criteria. A snippet is generated from the selected partitions. A response that includes the snippet is generated.

Abstract: A method and system of selecting reviews for display are described. Reviews for a subject are identified and an overall rating for the subject is determined. A subset of the identified reviews is selected based on the rating range in which the overall rating falls. The selection may also be based on zero or more other predefined criteria. A response that includes content from the selected reviews is generated. The content may include the full content or snippets of at least some of the selected reviews.

Abstract: A method and system of selecting reviews for display are described. Reviews for a subject are identified. A subset of the identified reviews is selected based on predefined quality criteria. The selection may also be based on zero or more other predefined criteria. A response that includes content from the selected reviews is generated. The content may include the full content or snippets of at least some of the selected reviews.