Abstract: Multimodal multilabel tagging of video content may include labeling the video content with topical tags that are identified based on extracted features from two or more modalities of the video content. The two or more modalities may include (i) a video modality for the object, images, and/or visual elements of the video content, (ii) a text modality for the speech, dialog, and/or text of the video content, and/or (iii) an audio modality for non-speech sounds and/or sound characteristics of the video content. Combinational multimodal multilabel tagging may include combining two or more features from the same or different modality in order to increase the contextual understanding of the features and generate contextually relevant tags. Video content may be labeled with global tags relating to overall topics of the video content, and different sets of local tags relating to topics at different segments of the video content.

Abstract: A method implemented by at least one server computer is provided, including: providing, over the Internet, access to a plurality of topics, wherein each topic includes, and further provides access to, a plurality of posted items; recording interaction data for the plurality of topics, the interaction data identifying user activity occurring within each of the topics; analyzing the interaction data to identify clusters of topics that exhibit similar behavioral patterns; for each cluster of topics, generating a community that includes the topics in the cluster; providing, over the Internet, access to the communities, wherein accessing a given community further provides access to the topics included in that community, which further provide access to the posted items that are included in the topics within that community.

Abstract: The present teaching relates to method, system, and programming for responding to an image related query. Information related to each of a plurality of images is received, wherein the information represents concepts co-existing in the image. Visual semantics for each of the plurality of images are created based on the information related thereto. Representations of scenes of the plurality of images are obtained via machine learning, based on the visual semantics of the plurality of images, wherein the representations capture concepts associated with the scenes.

Abstract: Multimodal multilabel tagging of video content may include labeling the video content with topical tags that are identified based on extracted features from two or more modalities of the video content. The two or more modalities may include (i) a video modality for the object, images, and/or visual elements of the video content, (ii) a text modality for the speech, dialog, and/or text of the video content, and/or (iii) an audio modality for non-speech sounds and/or sound characteristics of the video content. Combinational multimodal multilabel tagging may include combining two or more features from the same or different modality in order to increase the contextual understanding of the features and generate contextually relevant tags. Video content may be labeled with global tags relating to overall topics of the video content, and different sets of local tags relating to topics at different segments of the video content.

Abstract: A method implemented by at least one server computer is provided, including the following operations: receiving a plurality of training documents, each training document being defined by a sequence of words, each training document having one or more labels associated therewith; embedding the training documents, the words, and the labels in a vector space, wherein the embedding is configured to locate a given training document and its associated labels in proximity to each other in the vector space; embedding a new document in the vector space; performing a proximity search in the vector space to identify a set of nearest labels to the new document in the vector space; associating the nearest labels to the new document.

Abstract: Software for a website hosting short-text services creates an index of buckets for locality sensitive hashing (LSH). The software stores the index in an in-memory database of key-value pairs. The software creates, on a mobile device, a cache backed by the in-memory database. The software then uses a short text to create a query embedding. The software map the query embedding to corresponding buckets in the index and determines which of the corresponding buckets are nearest neighbors to the query embedding using a similarity measure. The software displays location types associated with each of the buckets that are nearest neighbors in a view in a graphical user interface (GUI) on the mobile device and receives a user selection as to one of the location types. Then the software displays the entities for the selected location type in a GUI view on the mobile device.

Abstract: A method implemented by at least one server computer is provided, including: providing, over the Internet, access to a plurality of topics, wherein each topic includes, and further provides access to, a plurality of posted items; recording interaction data for the plurality of topics, the interaction data identifying user activity occurring within each of the topics; analyzing the interaction data to identify clusters of topics that exhibit similar behavioral patterns; for each cluster of topics, generating a community that includes the topics in the cluster; providing, over the Internet, access to the communities, wherein accessing a given community further provides access to the topics included in that community, which further provide access to the posted items that are included in the topics within that community.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods provide systems and methods for automatic creation of a formatted, readable transcript of multimedia content, which is derived, extracted, determined, or otherwise identified from the multimedia content. The formatted, readable transcript can be utilized to increase accuracy and efficiency in search engine optimization, as well as identification of relevant digital content available for communication to a user.

Abstract: Disclosed are systems and methods for improving interactions with and between computers in content searching, generating, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to identify and retrieve data within or across platforms, which can be used to improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods provide systems and methods for automatic creation of a formatted, readable transcript of multimedia content, which is derived, extracted, determined, or otherwise identified from the multimedia content. The formatted, readable transcript can be utilized to increase accuracy and efficiency in search engine optimization, as well as identification of relevant digital content available for communication to a user.

Abstract: Disclosure includes an electronic message composition support system, method and architecture. Techniques including machine learning and natural language processing techniques are used to extend message composition capability and support and to provide feedback to a user regarding an error, condition, etc. detected in the user's message before the user sends the message, e.g., while the user is composing the message using a messaging application's user interface.

Abstract: An electronic message composition support system, method and architecture is provided. Techniques including machine learning and natural language processing techniques are used to extend message composition capability and support and to provide feedback to a user regarding an error, condition, etc. detected in the user's message before the user sends the message, e.g., while the user is composing the message using a messaging application's user interface.

Abstract: A method implemented by at least one server computer is provided, including the following operations: receiving a plurality of training documents, each training document being defined by a sequence of words, each training document having one or more labels associated therewith; embedding the training documents, the words, and the labels in a vector space, wherein the embedding is configured to locate a given training document and its associated labels in proximity to each other in the vector space; embedding a new document in the vector space; performing a proximity search in the vector space to identify a set of nearest labels to the new document in the vector space; associating the nearest labels to the new document.

Abstract: A method implemented by at least one server computer is provided, including: providing, over the Internet, access to a plurality of topics, wherein each topic includes, and further provides access to, a plurality of posted items; recording interaction data for the plurality of topics, the interaction data identifying user activity occurring within each of the topics; analyzing the interaction data to identify clusters of topics that exhibit similar behavioral patterns; for each cluster of topics, generating a community that includes the topics in the cluster; providing, over the Internet, access to the communities, wherein accessing a given community further provides access to the topics included in that community, which further provide access to the posted items that are included in the topics within that community.

Abstract: One or more computing devices, systems, and/or methods for entity disambiguation are provided. For example, a document may be analyzed to identify a first mention and a second mention. One or more techniques may be used to select and link a candidate entity, from a first set of candidate entities, to the first mention and select and link a candidate entity, from a second set of candidate entities, to the second mention.

Abstract: Software on a website hosting an online forum extracts a plurality of sub-dialogues from each thread in a corpus from the online forum. The software obtains one or more sub-dialogue annotations associated with each sub-dialogue. The sub-dialogue annotations include an annotation as to whether the sub-dialogue is constructive. The software extracts a plurality of features from each sub-dialogue uses them and the sub-dialogue annotations associated with the sub-dialogue to train a classifier that determines whether a particular sub-dialogue is constructive. Then the software obtains a new sub-dialogue from a thread currently displayed in the online forum and extracts the plurality of features from the new sub-dialogue. The software inputs the features extracted from the new sub-dialogue into the classifier and obtains a determination as to whether the new sub-dialogue is constructive.

Abstract: Software on a website serves a user of an online content aggregation service a first article that the user views. The software extracts named entities from the first article using a named-entity recognizer. The named-entity recognizer uses a sequence of word embeddings as inputs to a conditional random field (CRF) tool to assign labels to each of the word embeddings. Each of the word embeddings is associated with a word in the first article and is trained using an entire topical article from a corpus of topical articles as a context for the word. The software then creates rankings for articles ingested by the content aggregation service based at least in part on the named entities and serves the user a second article using the rankings.

Abstract: The present teaching relates to generating user profiles with semantic knowledge. A first information associated with a user is obtained. One or more entities are identified from the first information. The one or more entities are augmented based on second information to generate a set of augmented entities. The set of augmented entities are clustered into a set of hierarchical clusters. A set of user profiles is generated based on the set of hierarchical clusters so that the user profile is to be used to personalize content recommendation.

Abstract: Disclosure includes an electronic message composition support system, method and architecture. Techniques including machine learning and natural language processing techniques are used to extend message composition capability and support and to provide feedback to a user regarding an error, condition, etc. detected in the user's message before the user sends the message, e.g., while the user is composing the message using a messaging application's user interface.

Abstract: Software for a website hosting short-text services creates an index of buckets for locality sensitive hashing (LSH). The software stores the index in an in-memory database of key-value pairs. The software creates, on a mobile device, a cache backed by the in-memory database. The software then uses a short text to create a query embedding. The software map the query embedding to corresponding buckets in the index and determines which of the corresponding buckets are nearest neighbors to the query embedding using a similarity measure. The software displays location types associated with each of the buckets that are nearest neighbors in a view in a graphical user interface (GUI) on the mobile device and receives a user selection as to one of the location types. Then the software displays the entities for the selected location type in a GUI view on the mobile device.

Abstract: A method and system are disclosed for recognizing speech errors, such as in a spoken short messages, using an audio input device to receive an utterance of a short message, using an automated speech recognition module to generate a text sentence corresponding to the utterance, generating an N-best list of predicted error sequences for the text sentence using a linear-chain conditional random field (CRF) module, where each word of the text sentence is assigned a label in each of the predicted error sequences, and each label is assigned a probability score. The predicted error sequence labels are rescored using a metacost matrix module, the best rescored error sequence from the N-best list of predicted error sequences is selected using a Recognition Output Voting Error Reduction (ROVER) module, and a dialog action is executed by a dialog action module based on the best rescored error sequence and the dialog action policy.