Abstract: Embodiments may provide techniques to generate training data for summarization of complex documents, such as scientific papers, articles, etc., that are scalable to provide large scale training data. For example, in an embodiment, a method may be implemented in a computer system and may comprise collecting a plurality of video and audio recordings of presentations of documents, collecting a plurality of documents corresponding to the video and audio recordings, converting the plurality of video and audio recordings of presentations of documents into transcripts of the plurality of presentations, generating a summary of each document by selecting a plurality of sentences from each document using the transcript of the that document, generating a dataset comprising a plurality of the generated summaries, and training a machine learning model using the generated dataset.

Abstract: A method, computer system, and a computer program product for optimizing a plurality of personality traits of a virtual agent based on a predicted customer satisfaction value is provided. The present invention may include identifying a customer. The present invention may also include retrieving a plurality of data associated with the customer. The present invention may then include analyzing the received plurality of data using a customer satisfaction prediction model. The present invention may further include generating a plurality of analyzed data from the customer satisfaction prediction model based on the analyzed plurality of data. The present invention may also include generating a plurality of personality traits for a virtual agent from the generated plurality of analyzed data.

Abstract: Embodiments of the present systems and methods may provide techniques by which bots may be analyzed using improved representations of bot structure and a means of assessing conversational quality that may provide improved efficiency. For example a method may comprise training, at a computer system comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, a neural network model to learn representations that capture characteristics of the graphs of chatbots, wherein the captured characteristics include at least a content-based representation based on user utterances that are relevant to the nodes and based on the chatbot response for the nodes.

Abstract: Embodiments may provide techniques to generate training data for summarization of complex documents, such as scientific papers, articles, etc., that are scalable to provide large scale training data. For example, in an embodiment, a method may be implemented in a computer system and may comprise collecting a plurality of video and audio recordings of presentations of documents, collecting a plurality of documents corresponding to the video and audio recordings, converting the plurality of video and audio recordings of presentations of documents into transcripts of the plurality of presentations, generating a summary of each document by selecting a plurality of sentences from each document using the transcript of the that document, generating a dataset comprising a plurality of the generated summaries, and training a machine learning model using the generated dataset.

Abstract: Embodiments of the present systems and methods may provide techniques by which bots may be analyzed using improved representations of bot structure and a means of assessing conversational quality that may provide improved efficiency. For example a method may comprise training, at a computer system comprising a processor, memory accessible by the processor, and computer program instructions stored in the memory and executable by the processor, a neural network model to learn representations that capture characteristics of the graphs of chatbots, wherein the captured characteristics include at least a content-based representation based on user utterances that are relevant to the nodes and based on the chatbot response for the nodes.

Abstract: For each intent associated with a feature in a discordant conversation, one or more preceding discordant user utterances and one or more following discordant user utterances are collected. A discordant distribution over terms of the one or more preceding discordant user utterances and the one or more following discordant user utterances is created. For each intent associated with a feature in a non-discordant conversation, one or more preceding non-discordant user utterances and one or more following non-discordant user utterances are collected. A non-discordant distribution over terms of the one or more preceding non-discordant user utterances and the one or more following non-discordant user utterances is created. The discordant and non-discordant distributions are compared and the top-k terms that are most specific to user utterances associated with the corresponding discordance feature using Kullback-Leibler divergence are determined.

Abstract: Utilizing a computing device to detect and respond to emotion in dialog systems. The computing device receives a dialog structure comprising a plurality of dialog nodes. The computing device determines a node emotion level for each of the dialog nodes in the dialog structure based on analysis of one or more intents of each of the dialog nodes in the dialog structure. The computing device determines emotional hotspot nodes in the dialog structure, the node emotion level for each of the emotional hotspot nodes exceeding an emotional threshold. The computing device generates one or more responses modifying the node emotion level of each of the emotional hotspot nodes.

Abstract: For each intent associated with a feature in a discordant conversation, one or more preceding discordant user utterances and one or more following discordant user utterances are collected. A discordant distribution over terms of the one or more preceding discordant user utterances and the one or more following discordant user utterances is created. For each intent associated with a feature in a non-discordant conversation, one or more preceding non-discordant user utterances and one or more following non-discordant user utterances are collected. A non-discordant distribution over terms of the one or more preceding non-discordant user utterances and the one or more following non-discordant user utterances is created. The discordant and non-discordant distributions are compared and the top-k terms that are most specific to user utterances associated with the corresponding discordance feature using Kullback-Leibler divergence are determined.

Abstract: Utilizing a computing device to detect and respond to emotion in dialog systems. The computing device receives a dialog structure comprising a plurality of dialog nodes. The computing device determines a node emotion level for each of the dialog nodes in the dialog structure based on analysis of one or more intents of each of the dialog nodes in the dialog structure. The computing device determines emotional hotspot nodes in the dialog structure, the node emotion level for each of the emotional hotspot nodes exceeding an emotional threshold. The computing device generates one or more responses modifying the node emotion level of each of the emotional hotspot nodes.

Abstract: Utilizing a computing device to detect and respond to emotion in dialog systems. The computing device receives a dialog structure comprising a plurality of dialog nodes. The computing device determines a node emotion level for each of the dialog nodes in the dialog structure based on analysis of one or more intents of each of the dialog nodes in the dialog structure. The computing device determines emotional hotspot nodes in the dialog structure, the node emotion level for each of the emotional hotspot nodes exceeding an emotional threshold. The computing device generates one or more responses modifying the node emotion level of each of the emotional hotspot nodes.

Abstract: Utilizing a computing device to detect and respond to emotion in dialog systems. The computing device receives a dialog structure comprising a plurality of dialog nodes. The computing device determines a node emotion level for each of the dialog nodes in the dialog structure based on analysis of one or more intents of each of the dialog nodes in the dialog structure. The computing device determines emotional hotspot nodes in the dialog structure, the node emotion level for each of the emotional hotspot nodes exceeding an emotional threshold. The computing device generates one or more responses modifying the node emotion level of each of the emotional hotspot nodes.

Abstract: Technical solutions are described for generating structured conversational data. An example method includes receiving an utterance that is part of a conversation and identifying the utterance as part of an adjacency pair. The adjacency pair includes two utterances, each produced by different speakers. The method also includes associating the utterance with a label from a predetermined set of labels based on the identifying of the adjacency pair.

Abstract: According to some embodiments of the present invention there is provided a computerized method for labeling a cluster of text documents. The method comprises receiving a document cluster and producing automatically multiple document sub-clusters determined by randomly changing some documents. The method applies multiple cluster labeling algorithms on the cluster and on each sub-cluster, to generate ordered lists. The method comprises generating a ranked label list for each cluster labeling algorithm by computing automatically label values, one for each cluster label in the lists of the selected algorithm, and re-ranking the ordered list. The method combines the re-ranked label lists using a label fusing algorithm to produce a fused label list.

Abstract: A method, computer system, and a computer program product for optimizing a plurality of personality traits of a virtual agent based on a predicted customer satisfaction value is provided. The present invention may include identifying a customer. The present invention may also include retrieving a plurality of data associated with the customer. The present invention may then include analyzing the received plurality of data using a customer satisfaction prediction model. The present invention may further include generating a plurality of analyzed data from the customer satisfaction prediction model based on the analyzed plurality of data. The present invention may also include generating a plurality of personality traits for a virtual agent from the generated plurality of analyzed data.

Abstract: Technical solutions are described for generating structured conversational data. An example method includes receiving an utterance that is part of a conversation and identifying the utterance as part of an adjacency pair. The adjacency pair includes two utterances, each produced by different speakers. The method also includes associating the utterance with a label from a predetermined set of labels based on the identifying of the adjacency pair.

Abstract: Embodiments of the present invention provide systems and methods for detecting emotions with social media settings. Integral-based, emotion-based, and temporal-based features are used to assess the context of a dialogue between two parties. Social media features and textual features are also considered in order to detect the emotions of a party by assessing the popularity of the party and non-contextual factors within the dialogue, respectively.

Abstract: Technical solutions are described for generating structured conversational data. An example method includes receiving an utterance that is part of a conversation and identifying the utterance as part of an adjacency pair. The adjacency pair includes two utterances, each produced by different speakers. The method also includes associating the utterance with a label from a predetermined set of labels based on the identifying of the adjacency pair.

Abstract: Technical solutions are described for generating structured conversational data. An example method includes receiving an utterance that is part of a conversation and identifying the utterance as part of an adjacency pair. The adjacency pair includes two utterances, each produced by different speakers. The method also includes associating the utterance with a label from a predetermined set of labels based on the identifying of the adjacency pair.

Abstract: A method includes associating, in a graph including graph nodes connected via of edges, a respective node weight with each of the graph nodes, and organizing the graph nodes into ancestor nodes, each of the ancestor nodes having one or more descendent nodes so that the ancestor and the descendent nodes include all the graph nodes. For a given descendent node, a respective path to one or more of the ancestor nodes is identified, each of the respective paths including one or more edges, and a given ancestor node having a shortest of the identified paths is determined. A respective edge weight is assigned to each of the one or more edges in the shortest path, and, for the given descendent node, a node loss value is calculated based on the node weight and the respective edge weight of the each of the one or more edges.

Abstract: A method includes associating, in a graph including graph nodes connected via of edges, a respective node weight with each of the graph nodes, and organizing the graph nodes into ancestor nodes, each of the ancestor nodes having one or more descendent nodes so that the ancestor and the descendent nodes include all the graph nodes. For a given descendent node, a respective path to one or more of the ancestor nodes is identified, each of the respective paths including one or more edges, and a given ancestor node having a shortest of the identified paths is determined. A respective edge weight is assigned to each of the one or more edges in the shortest path, and, for the given descendent node, a node loss value is calculated based on the node weight and the respective edge weight of the each of the one or more edges.