Systems, methods, and non-transitory computer-readable storage media for generating concept data structures, and more specifically to forming a concept data structure which relies on a combination of text and visual data. A system can receive, from a user, a concept, along with instructions to generate a concept data structure around the concept. The system can then receive from a data set documents containing data associated with the concept. These documents are parsed, resulting in structured text. The system can also receive (from the same or another data set) images associated with the concept. These images are analyzed, resulting in image data. The system then generates a concept data structure using the parsed, structured text and the image data.

Systems, methods, and non-transitory computer-readable storage media for generating concept data structures, and more specifically to forming a concept data structure which relies on a combination of text and visual data. A system can receive, from a user, a concept, along with instructions to generate a concept data structure around the concept. The system can then receive from a data set documents containing data associated with the concept. These documents are parsed, resulting in structured text. The system can also receive (from the same or another data set) images associated with the concept. These images are analyzed, resulting in image data. The system then generates a concept data structure using the parsed, structured text and the image data.

Aspects of the technology employ a machine translation quality prediction (MTQP) model to refine datasets that are used in training machine translation systems. This includes receiving, by a machine translation quality prediction model, a sentence pair of a source sentence and a translated output (802). Then performing feature extraction on the sentence pair using a set of two or more feature extractors, where each feature extractor generates a corresponding feature vector (804). The corresponding feature vectors from the set of feature extractors are concatenated together (806). And the concatenated feature vectors are applied to a feedforward neural network, in which the feedforward neural network generates a machine translation quality prediction score for the translated output (808).

Automatic extractions of situations includes creating a situation image includes accessing a conversation between a first user and a second user, and generating an abstract knowledge graph at one or more textual levels. The method also includes generating one or more manifests by pruning the abstract knowledge graph and segmenting the pruned abstract knowledge graph. The method further includes converting the one or more manifests into the situation image.

Automatic extractions of situations includes creating a situation image includes accessing a conversation between a first user and a second user, and generating an abstract knowledge graph at one or more textual levels. The method also includes generating one or more manifests by pruning the abstract knowledge graph and segmenting the pruned abstract knowledge graph. The method further includes converting the one or more manifests into the situation image.

This disclosure relates to extraction of tasks from documents based on a weakly supervised classification technique, wherein extraction of tasks is identification of mentions of tasks in a document. There are several prior arts addressing the problem of extraction of events, however due to crucial distinctions between events-tasks, task extraction stands as a separate problem. The disclosure explicitly defines specific characteristics of tasks, creates labelled data at a word-level based on a plurality of linguistic rules to train a word-level weakly supervised model for task extraction. The labelled data is created based on the plurality of linguistic rules for a non-negation aspect, a volitionality aspect, an expertise aspect and a plurality of generic aspects. Further the disclosure also includes a phrase expansion technique to capture the complete meaning expressed by the task instead of merely mentioning the task that may not capture the entire meaning of the sentence.

A system for process shaping in a retail store environment comprises a video generation and processing component, a data source integration and aggregation component for aggregating and integrate information received from various sources, a process sensing component for generating one or more continuous processes, a process aggregator and weighing component for aggregating the one or more continuous processes into a merged weighted process, a proof of problem and value component for determining one or more process variations, a ripple effect analyser for sending one or more nudging messages to the retail store environment, and a gamified feedback algorithm component for communicating a nudging action corresponding to a nudging message, to one or more entities in the retail store environment.

Provided are a graph generation method and apparatus, a device, and a storage medium. The graph generation method comprises: parsing target logical information to obtain a plurality of logical elements; converting the plurality of logical elements into a syntax tree according to logic of the target logical information, where the syntax tree comprises a plurality of layers of tree nodes, and tree nodes between layers have a dependency relationship; converting the plurality of layers of tree nodes into a plurality of graph nodes; and connecting the plurality of graph nodes according to the dependency relationship to obtain a logical graph corresponding to the target logical information to allow a user to perform special effect editing based on the logic.

Provided are a graph generation method and apparatus, a device, and a storage medium. The graph generation method comprises: parsing target logical information to obtain a plurality of logical elements; converting the plurality of logical elements into a syntax tree according to logic of the target logical information, where the syntax tree comprises a plurality of layers of tree nodes, and tree nodes between layers have a dependency relationship; converting the plurality of layers of tree nodes into a plurality of graph nodes; and connecting the plurality of graph nodes according to the dependency relationship to obtain a logical graph corresponding to the target logical information to allow a user to perform special effect editing based on the logic.

Techniques are described herein for enabling autonomous agents to generate conclusive answers. An example of a conclusive answer is text that addresses concerns of a user who is interacting with an autonomous agent. For example, an autonomous agent interacts with a user device, answering user utterances, for example questions or concerns. Based on the interactions, the autonomous agent determines that a conclusive answer is appropriate. The autonomous agent formulates the conclusive answer, which addresses multiple user utterances. The conclusive answer provided to the user device.