Abstract: A computer-implemented method including: receiving, as input, a dataset comprising training pairs (s, t), wherein each training pair comprises (i) a source sentence s and (ii) a target paraphrase t of the source sentences; at a training stage, training a machine learning model on the dataset, to obtain a trained quality-controlled paraphrase generator model, wherein during the training stage, each of the training pairs is associated with a predicted control vector representing a predicted paraphrase quality of the source sentence in the training pair; and at an inference stage, inferencing the trained quality-controlled paraphrase generator model on an input sentence, wherein the input sentence is associated with an input quality control vector, to obtain an output paraphrase of the input sentence which conforms to the quality control vector.

Abstract: Systems and techniques that facilitate context-aware edit management of webpage-based applications are provided. In various embodiments, a system can detect an edit made to a webpage. In various aspects, the system can determine whether a webpage-based application associated with the webpage is consistent with the edit, based on a registry that respectively maps outputs of the webpage-based application to source texts and corresponding semantic contexts of a pre-edit version of the webpage.

Abstract: A table-to-text (T2T) generation model provides type control and semantic diversity. A method, system, and computer program product are configured to: train a model to generate one or more logic-type-specific natural language statements based on tabular data; in response to receiving a first input comprising first input data with a user-specified logic-type, the trained model generating a first logic-type-specific natural language statement based on the first input data and the user-specified logic-type; and in response to receiving a second input comprising second input data without a user-specified logic-type, the trained model generating plural second logic-type-specific natural language statements based on the second input data, wherein respective ones of the second logic-type-specific natural language statements are generated according to respective ones of plural predefined logic-types.

Abstract: A computer-implemented method comprising: receiving data comprising: a question provided by a user, a list that constitutes a direct answer to the question, and an introductory text to the list; using a first machine learning model to classify the introductory text as redundant or nonredundant, based on the data; using a second machine learning model to classify the list as belonging to a certain list type out of multiple list types, based on the list; and providing to the user: (a) the introductory text, only if the introductory text has been classified as nonredundant, (b) all or only a subset of the items of the list, (c) an indication as to the number of non-provided items of the list or the number of all items of the list, if only a subset of the items is being provided in (b), and (d) a description of the certain list type.

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.