Abstract: In one aspect, the present disclosure relates to a method which, in one example embodiment, can include receiving text data that includes at least unstructured data and wherein the text data is associated with a plurality of messages communicated between a plurality of entities. The method can also include determining relationships between the entities, based on the text data associated with the plurality of messages, and generating, from a knowledge base assembled from at least the text data, a response to a user interaction representing a query for information that corresponds to at least one of the entities and indicates information on one or more of the determined relationships between the entities. The method can also include detecting a deviation in communication between the entities that indicates unauthorized disclosure of information between a first entity and a second entity.

Abstract: Some aspects of the present disclosure relate to systems and methods for identifying potential violation conditions from electronic communications. In one embodiment, a method includes receiving data associated with an electronic communication and detecting, from the received data, and using a trainable model, an indicator of a potential violation condition, where the violation condition is associated with an activity that is a violation of a predetermined standard. The method also includes, responsive to detecting the indicator of the potential violation condition, marking the electronic communication as being associated with a potential violation condition, and presenting the potential violation condition to a user for review.

Abstract: In one aspect, the present disclosure relates to a method which, in one example embodiment, can include reading text data corresponding to messages and creating semantic annotations to the text data to generate annotated messages. Creating the semantic annotations can include generating, at least in part by at least one trained statistical language model, predictive labels as annotations corresponding to language patterns associated with the text data. The method further includes aggregating the annotated messages and storing information associated with the aggregated annotated messages in a message store, and performing, based on information from the message store and associated with the messages, global analytics functions.

Abstract: In some aspects, the present disclosure relates to neural language modeling. In one embodiment, a computer-implemented neural network includes a plurality of neural nodes, where each of the neural nodes has a plurality of input weights corresponding to a vector of real numbers. The neural network also includes an input neural node corresponding to a linguistic unit selected from an ordered list of a plurality of linguistic units, and an embedding layer with a plurality of embedding node partitions. Each embedding node partition includes one or more neural nodes. Each of the embedding node partitions corresponds to a position in the ordered list relative to a focus term, is configured to receive an input from an input node, and is configured to generate an output.

Abstract: In one aspect, the present disclosure relates to a method which, in one embodiment, includes: receiving video data for a first video and deconstructing the video data of the first video into a plurality of context windows; performing, on each context window of the plurality of context windows that includes an image frame, a video analytic function on the image frame to identify one or more characteristics of the context window that are associated with image-related content of the first video; performing, on each context window of the plurality of context windows that includes an audio frame, a video analytic function on the audio frame to identify one or more characteristics of the context window that are associated with audio-related content of the first video; generating, for each of the plurality of context windows, a respective local atomic unit comprising attributes derived from the identified one or more characteristics of the respective context window, to form a plurality of local atomic units; and gen

Abstract: A system and method for processing information in unstructured or structured form, comprising a computer running in a distributed network with one or more data agents. Associations of natural language artifacts may be learned from natural language artifacts in unstructured data sources, and semantic and syntactic relationships may be learned in structured data sources, using grouping based on a criteria of shared features that are dynamically determined without the use of a priori classifications, by employing conditional probability constraints.

Abstract: Some aspects of the present disclosure relate to systems and methods for identifying potential violation conditions from electronic communications. In one embodiment, a method includes receiving data associated with an electronic communication and detecting, from the received data, and using a trainable model, an indicator of a potential violation condition, where the violation condition is associated with an activity that is a violation of a predetermined standard. The method also includes, responsive to detecting the indicator of the potential violation condition, marking the electronic communication as being associated with a potential violation condition, and presenting the potential violation condition to a user for review.

Abstract: In one aspect, the present disclosure relates to a method which, in one embodiment, includes: receiving video data for a first video; deconstructing the video data of the first video into a plurality of context windows; performing, on each context window that includes an image frame, a video analytic function on the image frame to identify one or more characteristics of the context window; performing, on each context window that includes an audio frame, a video analytic function on the audio frame to identify one or more characteristics of the context window; generating, for each context windows, a respective local atomic unit comprising attributes derived from the identified one or more characteristics of the respective context window, to form a plurality of local atomic units; and generating a local graph representation of the first video, comprising a plurality of nodes corresponding to the plurality of local atomic units.

Abstract: In one aspect, the present disclosure relates to a method which, in one example embodiment, can include reading text data corresponding to messages and creating semantic annotations to the text data to generate annotated messages. Creating the semantic annotations can include generating, at least in part by at least one trained statistical language model, predictive labels as annotations corresponding to language patterns associated with the text data. The method further includes aggregating the annotated messages and storing information associated with the aggregated annotated messages in a message store, and performing, based on information from the message store and associated with the messages, global analytics functions.

Abstract: In some aspects, systems, methods, and computer-readable media for selective feature activation for coreference resolution are disclosed. In one embodiment, a method includes receiving text data comprising a plurality of mentions corresponding to entities, and determining a plurality of data features, comprising semantic features and syntactic features, for comparing a particular pair of mentions from the plurality of mentions. The method also includes selectively activating a subset of features from the plurality of data features based on semantic and syntactic context of the particular pair of mentions within the text data, and determining, using weights associated with the activated subset of features and at least one machine learning function, whether a first mention of the pair of mentions and second mention of the pair of mentions refer to a same entity.

Abstract: In some aspects, the present disclosure relates to coreference resolution. In one embodiment, a method includes obtaining unstructured text data including a plurality of references corresponding to entities, and determining, from the unstructured text data, attributes associated with the entities. The method also includes obtaining structured data including predefined attributes associated with the entities, and comparing attributes associated with a first coreference unit with attributes associated with a second coreference unit. The first coreference unit is a sub-entity representation having the attributes determined from the unstructured text data and the second coreference unit is a sub-entity representation having the predefined attributes. The method further includes determining, based on the comparison, whether the first coreference unit and the second coreference unit both correspond to the same entity.

Abstract: In one aspect, the present disclosure relates to a method which, in one example embodiment, can include reading text data corresponding to messages, creating semantic annotations to the text data to generate one or more annotated messages, and aggregating the annotated messages and storing information associated with the aggregated annotated messages in a message store. The method can further include performing, based on information from the message store and associated with the one or more messages, one or more global analytics functions that include: identifying an annotation error in the semantic annotations created using the trained statistical language model, updating the respective semantic annotation to correct the annotation error, and back-propagating corrected data corresponding to the updated semantic annotation into training data for further language model training.

Abstract: Systems and methods for coreference resolution are disclosed. In one embodiment, a method includes locating, for each of a selected plurality of chains of coreferent mentions, a particular context-based name from the respective chain, wherein the coreferent mentions correspond to entities and the context-based name is a longest name in the respective chain, a last name in the respective chain, or a most frequently occurring name in the respective chain. The method also includes determining an entity category for each respective one of the plurality of chains and determining one or more entity attributes from structured data and unstructured data. The method further includes, based on the located particular context-based name, the entity category, and the one or more attributes, assigning high-probability coreferent chains to high-confidence buckets, such as to produce a Zipfian-like distribution having a head region and a tail region.

Abstract: A system and method for processing information in unstructured or structured form, comprising a computer running in a distributed network with one or more data agents. Associations of natural language artifacts may be learned from natural language artifacts in unstructured data sources, and semantic and syntactic relationships may be learned in structured data sources, using grouping based on a criteria of shared features that are dynamically determined without the use of a priori classifications, by employing conditional probability constraints.

Abstract: According to one aspect, a method for machine learning management is provided. In one embodiment, the method includes receiving a first segment of text data, identifying data features corresponding to a sequence of characters in the first segment of text data, and generating predictive annotations to the sequence of characters based at least in part on the identified data features. The method can also include identifying inaccurate annotations generated according to the predictive annotations, correcting the identified inaccurate annotations, generating one or more sets of model training data incorporating the corrected annotations, and monitoring progress of annotations made to a second segment of text data associated with the first segment of text data by a plurality of collaborating users of a plurality of managed computers.

Abstract: According to one aspect, a computer-implemented method for entity resolution is disclosed. In one embodiment, the method includes generating a semantic hash for an entity having an assigned entity identifier (ID) and, upon the occurrence of an entity milestone, changing the entity ID. The method further includes generating a semantic hash for the entity having the changed entity ID, and maintaining history information associated with the entity and corresponding entity IDs and semantic hashes over a period of time that includes a plurality of entity milestones. The method also includes periodically removing at least one set of older entities and retaining entity IDs and semantic hashes associated with the removed entities.

Abstract: According to one aspect, a method for coreference resolution is provided. In one embodiment, the method includes receiving a segment of text that includes mentions corresponding to entities. A first feature vector is generated based on one or more features associated with a first mention, and a second feature vector is generated based on based on one or more features associated with a second mention. A measure of similarity between the first feature vector and second feature vector is computed and, based on the computed measure of similarity, it is determined if the first mention and the second mention both correspond to the same entity.