Abstract: According to an aspect of an embodiment, operations include controlling a user device to display a plurality of task-specific questions onto an electronic user interface (UI) of the user device. Each task-specific question corresponds to a check for presence of a bias in one of a sequence of development phases of a machine learning (ML) model. The operations further include receiving a first input comprising a plurality of user responses corresponding to the displayed plurality of task-specific questions and determining a set of biases associated with the ML model based on the received first input. The operations further include controlling the user device to display the determined set of biases and a set of plausible actions to mitigate an effect of the determined set of biases on the ML model.

Abstract: According to an aspect of an embodiment, a method may include obtaining a data set that includes categories (or features), and a target criteria. The method may further include obtaining a first decision tree model using the data set. The method may further include ranking the categories based on the first decision tree model and removing low-ranking categories from the data set. The method may further include generating a second decision tree model using the data set. The second decision tree model may include branch nodes. Each of branch nodes may represent a branch criteria. The method may further include pruning a branch node. The method may further include designating a remaining branch nodes as a rule node. The method may further include generating a rule based on the branch criteria of the rule node and presenting the rule in a graphical user interface.

Abstract: A method may include obtaining a data set for analysis, and selecting at least one candidate of bias for predicting whether the data set includes a result that is biased based on the candidate. The method may also include generating a point cloud of the data set based on the candidate and the result. The method may additionally include computing, prior to performing classification on the data set using machine learning, persistence homology on the point cloud based on the candidate and the result. The method may also include plotting persistence barcodes based on the persistence homology, where the persistence barcodes may be indicative of a duration of complexes within the persistence homology, determining a length of a longest barcode in the persistence barcodes, and generating a quantification of the bias based on the longest barcode and a visualization of the bias based on the plot of the persistence barcodes.

Abstract: A method of automated inquiry response includes forming clusters that represent a meaning. The method includes assigning a level of sophistication to the clusters and generating sub-clusters within the clusters that represent a sentiment or a level of sophistication. The method includes assigning responses to the sub-clusters that address the meaning of the cluster and are modified based on the sentiment or a level of sophistication. The method includes computing a substantive issue, a sentiment, and a level of sophistication of a received inquiry. The method includes identifying clusters to which the inquiry pertains and generating an order of the identified clusters based on the assigned level of sophistication. The method includes crowdsourcing a comparison of the substantive issue of the inquiry to meanings of the identified clusters. The method includes offering a response associated with one of the identified clusters and with the sub-cluster for the identified sentiment.

Abstract: A method may include obtaining a dialogue of a user and a pre-trained language model. The method may include obtaining a corpus of dialogues and a corpus of response materials. The method may include modifying the pre-trained language model. The method may include identifying a dialogue topic of the dialogue of the user and identifying a set of response topics. The method may include selecting a set of response materials from the corpus of response materials. The method may include determining a first plurality of probabilities and, for each response material of the set of response materials, a respective second plurality of probabilities. The method may include comparing the first plurality of words with each respective second plurality of words associated with each respective response material of the set of response materials. The method may include selecting a response material of the set of response materials based on the comparison.

Abstract: According to an aspect of an embodiment, operations include receiving user information comprising motion information associated with a group of users in a built environment and user preference information associated with a group of events hosted in the built environment. The operations further include receiving layout information associated with the built environment and schedule information associated with the group of events. The operations further include predicting event-specific action associated with each user based on the user information, and the layout and schedule information. The operations further include predicting a path for navigation towards an event location associated with one of the group of events based on the predicted event-specific action and historical movement information of the group of users. The operations further include selecting, from the predicted paths, one or paths for navigation and generating navigation suggestions based on the selected paths.

Abstract: A method of estimating one or more conditional probabilities may be provided. A method may include determining one or more states based on user input, and determining a similarity measurement between at least one state pair of one or more state pairs. The method may further include determining a likelihood of probability for the at least one state pair of the one or more state pairs. Moreover, the method may include estimating a conditional probability for the at least one state pair of the one or more state pairs based on the determined likelihood of probability and the determined one or more states.

Abstract: A method may include directing display of a dataset menu listing datasets representative of graphs. The method may include identifying features in the datasets as corresponding to nodes and edges. The method may include selecting local or global mapping to map categorical feature values to numeric values. Local mapping may be selected in response to a distribution of feature values not corresponding across different graphs. Global mapping may be selected in response to a distribution of the feature values corresponding across different graphs. The method may include directing display of configuration settings that indicate the selection between local and global mapping for training a classification model. The method may include obtaining selected configuration settings. The method may include providing the selected configuration settings and datasets to a machine learning backend, which may utilize the machine learning algorithm, datasets, and selected configuration settings to train the classification model.

Abstract: According to an aspect of an embodiment, operations include receiving user information comprising motion information associated with a group of users in a built environment and user preference information associated with a group of events hosted in the built environment. The operations further include receiving layout information associated with the built environment and schedule information associated with the group of events. The operations further include predicting event-specific action associated with each user based on the user information, and the layout and schedule information. The operations further include predicting a path for navigation towards an event location associated with one of the group of events based on the predicted event-specific action and historical movement information of the group of users. The operations further include selecting, from the predicted paths, one or paths for navigation and generating navigation suggestions based on the selected paths.

Abstract: A method includes storing a plurality of textual conversations. Each textual conversation of the plurality of textual conversations corresponds to a plurality of textual messages shared between a plurality of agents and a plurality of customers. The method further includes retrieving a first set of textual conversations of a first time-period from the stored plurality of textual conversations. The first set of textual conversations correspond to a first agent of the plurality of agents. Further, the method includes determining a first set of features of each textual message in the retrieved first set of textual conversations of the first time-period. Furthermore, the method includes determining a first creativity score for the first agent based on the determined first set of features of the first set of textual conversations and generating behavioral communicative information, related to the first agent based on the determined first creativity score.

Abstract: According to an aspect of an embodiment, operations include controlling a user device to display a plurality of task-specific questions onto an electronic user interface (UI) of the user device. Each task-specific question corresponds to a check for presence of a bias in one of a sequence of development phases of a machine learning (ML) model. The operations further include receiving a first input comprising a plurality of user responses corresponding to the displayed plurality of task-specific questions and determining a set of biases associated with the ML model based on the received first input. The operations further include controlling the user device to display the determined set of biases and a set of plausible actions to mitigate an effect of the determined set of biases on the ML model.

Abstract: Technologies are described to provide autonomous speech and language assessments. In some examples, a method to conduct an autonomous speech and language assessment includes facilitating authoring of an autonomous speech and language assessment. The autonomous speech and language assessment may be interactions between one or more of a conversational module, an analytical module, and a control module, and the interaction may be specified using a visual programming language. The method may also include modeling the autonomous speech and language assessment as a graph using a conversation markup language, and conducting the autonomous speech and language assessment utilizing a conversational virtual agent.

Abstract: A method may include obtaining a dialogue of a user and a pre-trained language model. The method may include obtaining a corpus of dialogues and a corpus of response materials. The method may include modifying the pre-trained language model. The method may include identifying a dialogue topic of the dialogue of the user and identifying a set of response topics. The method may include selecting a set of response materials from the corpus of response materials. The method may include determining a first plurality of probabilities and, for each response material of the set of response materials, a respective second plurality of probabilities. The method may include comparing the first plurality of words with each respective second plurality of words associated with each respective response material of the set of response materials. The method may include selecting a response material of the set of response materials based on the comparison.

Abstract: A method of generating text using an adversarial network includes receiving a limited dataset. The limited dataset includes real data having actual parameters and actual sentences. The method includes receiving content data that includes a concept related to a portion of the real data or that causes an issue of the real data. The method includes generating relationships between the real data and the content data. The method includes embedding the content data with the real data in an encoder output that includes content vector embedding. The method includes generating an additional parameter set that includes additional parameters and one or more additional statements. The additional parameter set may be supplemental to the real data and configured to enhance an expressiveness of a model. The method includes generating explanatory statement based on the additional parameter set and the relationships.

Abstract: A method of generating text having related purposes using a generative adversarial network (GAN) includes receiving a limited dataset including real data with related cognitive value types (types). The method includes applying loss functions to portions of the real data. The portions of the real data are each identified as having one of the types. The loss functions ensure alignment of the portions with corresponding types. The method includes embedding the real data into an encoder output that includes an embedded vector for the cognitive value types. The method includes generating an additional parameter set supplemental to the real data and configured to enhance an expressiveness of a model. The method includes generating statements based on the additional parameter set and the encoder output. The statements include a style of one of the cognitive value types and are related to a common issue addressed by the GAN.

Abstract: A method of generating a report for a digital task is provided. The method may include receiving an identification of a digital task initiated by a user, and electronically monitoring at least one of user interaction with at least one application while the user performs the digital task via an electronic system and a state of the electronic system while the user performs the digital task via the electronic system. Further, the method may include capturing a plurality of snapshots for the digital task. Each snapshot of the plurality of snapshots may include information for at least of one or more user actions and the state of the electronic system while the user performs the digital task. The method may also include generating a report for the digital task including the plurality of snapshots.

Abstract: A method of real peak detection includes optimizing a scoring function using training signals with known peaks and known features. The method includes receiving an input signal measured from a mobile sensor and representative of a cyclic biological process. The method includes filtering the input signal to remove low and high frequency noise. The method includes identifying candidate peaks and troughs within a selected time range of the input signal. The method includes extracting a feature that describes properties of the two or more candidate peaks. The method includes scoring the candidate peaks using the scoring function, selecting a real peak as the candidate peak with the highest score, and generating a biologic interval data set with the real peak and another peak that is representative of health markers. The method includes assessing a condition of the patient based on the biologic interval data set.

Abstract: An embodiment includes a method of learner engagement that includes crowdsourcing a skill proposal. The skill proposal is crowdsourced and includes a skill item that describes an exercise related to an educational concept. The method may include crowdsourcing a real-world problem proposal. The real-world problem proposal may include a real-world problem item that includes one or more technical issues that occur in at least one career. The method may include determining whether the skill item is relevant to the real-world problem item based on application of the educational concept of the skill item to technical issues of the real-world problem item. In response to a determination that the skill item is relevant to the real-world problem item, the method may include pairing the skill item with the real-world problem item.

Abstract: A method may include obtaining a data set for analysis, and selecting at least one candidate of bias for predicting whether the data set includes a result that is biased based on the candidate. The method may also include generating a point cloud of the data set based on the candidate and the result. The method may additionally include computing, prior to performing classification on the data set using machine learning, persistence homology on the point cloud based on the candidate and the result. The method may also include plotting persistence barcodes based on the persistence homology, where the persistence barcodes may be indicative of a duration of complexes within the persistence homology, determining a length of a longest barcode in the persistence barcodes, and generating a quantification of the bias based on the longest barcode and a visualization of the bias based on the plot of the persistence barcodes.

Abstract: A method may include receiving a goal of a user. The method may also include obtaining progress data related to accomplishment of the goal by the user from a sensor. The method may further include determining, based on the progress data, a progress level of the first user. The progress level may correspond to progress of the first user with respect to accomplishment of the goal. Moreover, the method may include generating a conversation with the user by a virtual agent based on the progress level.