Abstract: In one example, a system can receive a set of text samples and generate a set of summaries based on the set of text samples. The system can then generate a training dataset by iteratively executing a training-sample generation process. Each iteration can involve selecting multiple text samples from the set of text samples, combining the multiple text samples together into a training sample, determining a text category and a summary corresponding to a selected one of the multiple text samples, and including the text category and the summary in the training sample. After generating the training dataset, the system can use it to train a model. The trained model can then receive a target textual dataset and a target category as input, identify a portion of the target textual dataset corresponding to the target category, and generate a summarization of the portion of that target textual dataset.

Abstract: In one example, a system can execute a first machine-learning model to determine an overall classification for a textual dataset. The system can also determine classification scores indicating the level of influence that each token in the textual dataset had on the overall classification. The system can select a first subset of the tokens based on their classification scores. The system can also execute a second machine-learning model to determine probabilities that the textual dataset falls into various categories. The system can determine category scores indicating the level of influence that each token had on a most-likely category determination. The system can select a second subset of the tokens based on their category scores. The system can then generate a first visualization depicting the first subset of tokens color-coded to indicate their classification scores and a second visualization depicting the second subset of tokens color-coded to indicate their category scores.

Abstract: A system trains a classification model. Text windows are defined from tokens based on a window size. A network model including a transformer network is trained with the text windows to define classification information. A first accuracy value is computed. (A) The window size is reduced using a predefined reduction factor value. (B) Second text windows are defined based on the reduced window size. (C) Retrain the network model with the second text windows to define classification information. (D) A second accuracy value is computed. (E) An accuracy reduction value is computed from the second accuracy value relative to the first accuracy value. When the computed accuracy reduction value is ?an accuracy reduction tolerance value, repeat (A)-(E) until the accuracy reduction value is <the accuracy reduction tolerance value. Otherwise, increase the window size, define final text windows based on the increased window size, and retrain the network model.

Abstract: A system determines user intent from text. A conversation element is received. An intent is determined by matching a domain independent relationship and a domain dependent term determined from the received conversation element to an intent included in an intent database that stores a plurality of intents and by inputting the matched intent into a trained classifier that computes a likelihood that the matched intent is the intent of the received conversation element. An action is determined based on the determined intent. A response to the received conversation element is generated based on the determined action and output.

Abstract: A search engine is enhanced to employ user preferences to customize answer output by, receiving a first plurality of candidate answers and weights to a first search query for a first user from a first stage of a non-semantic search engine routing and processing path; augmenting the weights for the plurality of candidate answers according to a set of preference coefficients according to a first set of preferences for the first user; selecting one or more of the first plurality of candidate answers according to the augmented weights; and producing an output including the selected one or more candidate answers.

Abstract: A system determines user intent from text. A conversation element is received. An intent is determined by matching a domain independent relationship and a domain dependent term determined from the received conversation element to an intent included in an intent database that stores a plurality of intents and by inputting the matched intent into a trained classifier that computes a likelihood that the matched intent is the intent of the received conversation element. An action is determined based on the determined intent. A response to the received conversation element is generated based on the determined action and output.

Abstract: A search engine is enhanced to employ user preferences to customize answer output by, receiving a first plurality of candidate answers and weights to a first search query for a first user from a first stage of a non-semantic search engine routing and processing path; augmenting the weights for the plurality of candidate answers according to a set of preference coefficients according to a first set of preferences for the first user; selecting one or more of the first plurality of candidate answers according to the augmented weights; and producing an output including the selected one or more candidate answers.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A visualization of literary elements of a work of literature, such as a novel or short story, is generated from meta-data records representing a digital work of literature including literary elements (humor, drama, adventure, etc.), characters, and plot devices related to a position within the work of literature where each appears. A significance level is determined for each of the elements, characters and plot devices at each position within the work of literature, and these are plotted into a sequential graph having position (e.g. timeline) axis and a significance level axis. The sequential graph is then output for printing or display. Human-generated and machine-generated meta-data may be ingested equally well by the method. Colors, line thickness, and a broken line patterns may be employed for greater visual meaning. And, the sequential graph may be annotated according to segments (e.g. chapters, sections) and dominant genre within each segment.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.

Abstract: A semantic search engine is enhanced to employ user preferences to customize answer output by, for a first user, extracting user preferences and sentiment levels associated with a first question; receiving candidate answer results of a semantic search of the first question; weighting the candidate answer results according to the sentiment levels for each of the user preferences; and producing the selected candidate answers to the first user. Optionally, user preferences and sentiment levels may be accumulated over different questions for the same user, or over different users for similar questions. And, supplemental information may be retrieved relative to a user preference in order to further tune the weighting per the preferences and sentiment levels.