Abstract: Disclosed herein are system, method, and computer program product embodiments for recognizing a human emotion in a message. An embodiment operates by receiving a message from a user. The embodiment labels each word of the message with a part of speech (POS) thereby creating a POS set. The embodiment determines an incongruity score for a combination of words in the POS set using a knowledgebase. The embodiment determines a preliminary emotion detection score for an emotion for the message based on the POS set. Finally, the embodiment calculates a final emotion detection score for the emotion for the message based on the preliminary emotion detection score and the incongruity score.

Abstract: A method, system and computer-usable medium are disclosed for reducing labeled data imbalances when training an active learning system. The ratio of instances having positive labels or negative labels in a collection of labeled instances associated with an input category used for learning is determined. A first instance for annotation is selected from a collection of unlabeled instances if a first threshold for negative instances, and a first threshold confidence level of being a positive instance of the input category, have been met. A second instance for annotation is selected if a second threshold for positive instances, and a second threshold confidence level of being a negative instance of the input category, have been met. The first and second instances are respectively annotated with a positive and negative label and added to the collection of labeled instances, which are then used for training.

Abstract: Techniques are described for providing information during a service session, using an intelligent agent. The intelligent agent executes as a process to monitor communications exchanged during a service session between an individual and a service representative (SR) within a service environment. The agent analyzes the communications to identify questions or other topics that are posed by the individual during the service session. The agent retrieves stored data related to such questions or other topics, and generates a message to address each question or other topic. The message is injected into the service session to be presented to the individual, to supplement the conversation that is taking place between the SR and the individual. In some implementations, the agent monitors the communications, generates the message, and/or injects the message into the service session at least partly autonomously of any explicit action taken by the SR.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for managing dialogs. In one aspect, a method includes receiving a request associated with a task from a user device; submitting the request to each of a plurality of distinct data providers; receiving a plurality of suggested dialog responses from two or more of the data providers; scoring the one or more suggested dialog responses based on one or more scoring factors; determining a particular dialog response to provide to the user based on the scoring; and providing the determined dialog response to the user device.

Abstract: A facility for representing a mandate occurring in an authority document with a control is described. For each of one or more controls in a set of existing controls, the facility determines a similarity score measuring the similarity of the mandate and the control; where the similarity score exceeds a similarity threshold, the facility links the mandate to the control. Where the mandate is not linked to any control in the set of controls, the facility adds a control to the set of controls that is based on the mandate, and links the mandate to the added control.

Abstract: A method includes displaying a suggestion region above an on-screen keyboard. The suggestion region includes multiple suggested character strings. The method further includes: detecting a gesture that begins within a predefined key of the on-screen keyboard; and responsive to detecting the gesture: in accordance with a determination that the gesture ends within the predefined key, inserting a first character string into a text field; and in accordance with a determination that the gesture ends outside of the predefined key, inserting a second character string into the text field, wherein the second character string is different from the first character string.

Abstract: Disclosed herein are system, method, and computer program product embodiments for training a machine learning model and using the machine learning model to determine an intent associated with an utterance. An embodiment operates by receiving an utterance, determining a first vector based on the received utterance, and determining a second vector based on the received utterance. A third vector is generated by concatenating the first vector and the second vector. The third vector is used to perform at least one of classifying, using a machine learning model, the utterance to determine the intent associated with the utterance or training the machine-learning model.

Abstract: The present invention is a system and method for optimizing the narrative text generated by one or more narrative frameworks that utilize data input from one or more data sources to drive the creation of a narrative text output. Narrative text is generated in accordance with sets of data that provide the scope of text to be generated. A Quality Assurance module presents the narrative text output to a user that reviews both the condition and the logic evaluation associated with the scope, and the quality of the generated text. A log of Quality Assurance items is created upon review of the generated text. These items are then later resolved by locating them in a narrative text generation data structure to resolve the identified issues.

Abstract: In one embodiment, a method includes receiving an initial input in a first modality from a first user from a client system associated with the first user, determining one or more intents corresponding to the initial input by an intent-understanding module, generating one or more candidate continuation-inputs based on the one or more intents, where the one or more candidate continuation-inputs are in one or more candidate modalities, respectively, and wherein the candidate modalities are different from the first modality, and sending instructions for presenting one or more suggested inputs corresponding to one or more of the candidate continuation-inputs to the client system.

Abstract: A portable electronic device having a touch screen display performs a set of operations, including displaying a plurality of key icons, each having an adjustable size hit region, and receiving a sequence of individual touch points input by a user on the touch screen display. The operations performed by the device further include processing the received individual touch points by: forming a user-input directed graph for the sequence of individual touch points received so far, determining a character corresponding to a last received individual touch point in accordance with the adjustable hit regions of the displayed key icons, displaying a sequence of characters corresponding to the sequence of individual touch points, and updating sizes of the adjustable hit regions for a plurality of the key icons in accordance with the sequence of individual touch points input by the user.

Abstract: A database querying system, comprising an input interface unit configured to receive textual input and to convert the textual input into a textual data string, a sequencing unit configured to obtain at least one key phrase from the textual data string and to obtain for each of the at least one key phrase a set of all contiguous sequences of words of the respective key phrase, a classification network unit configured to access a semantic network for each of the contiguous sequences of words, wherein the classification network unit is configured to set a classification flag for the respective contiguous sequence of words, if the semantic network contains a link between the respective contiguous sequence of words and an entry in a predetermined classification database; a comparison unit configured to access a predetermined target database for each of the contiguous sequences of words, wherein the comparison unit is configured to set a target flag for the respective contiguous sequence of words, if the predetermi

Abstract: Embodiments are directed to a system, computer program product, and method for application of cognitive processing to a communication, and selectively transmitting the communication based on the cognitive processing. Natural language understanding (NLU) decomposes the communication to identify content and keywords. A dictionary determined to be contextually related to the communication is identified to support and enable a multi-dimensional analysis of the communication content. The communication is subject to dynamic filtering with support of the dictionary and dictionary content, and the dictionary is subject to a selective amendment based on the dynamic processing. A response is generated from the filtering, and the response is subject to selective transmission.

Abstract: A method for automatically processing log files of different types of an automation system, said method determining a message part of a data set of the log file. All contents of the respective data sets of the log files are concatenated. The data sets of all the log files are summarized in a summary file. The data sets of all the log files are chronologically sorted in the summary file. The data sets are compressed in the summary file. The compressed data sets in the summary file are coded. The compressed data sets are assigned to groups with associated group codes. The group code of the assigned group is decoded. The decoded group code is output as the alphanumeric message part of the log file. The alphanumeric message part of the log file is stored in a memory.

Abstract: A set of candidate intent vectors is generated from an input intent vector. A validation of the set of candidate intent vectors is performed that selects as valid intent vectors any of the set of candidate intent vectors that are semantically similar to the input intent vector.

Abstract: Examples of techniques for constructing, evaluating, and improving a search string for retrieving images are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method includes receiving, by a processing device, a plurality of images returned as results to an executed search string in the form of a tuple including an item class, an action and an actor. The method further includes generating, by the processing device, a collection similarity score by comparing at least one of the plurality of images to at least one other of the plurality of images. The method further includes determining, by the processing device, whether the collection similarity score exceeds a collection threshold. The method further includes, based at least in part on determining that the similarity score does not exceed the collection threshold, indicating that the search string is ineffective at indicating the item use.

Abstract: Techniques are presented for producing demographics, in an automated fashion, from a search result of computer-accessible content. While the demographics can be determined for a research product that has been produced by any technique, they are particularly useful when applied to an automated frame-based search approach. Frame-based search engines are presented for technology profiling, healthcare-related search and brand research. Determination of a demographic proceeds at two levels: member and population. At the member level, a demographic characteristic can be determined applicable with either total or partial certainty. Each value assigned by a demographic, to a population member, has a confidence level associated with it and the assignments can be represented by a Confidence Distribution. Summarization of a demographic, at the population level, depends upon whether the certainty assignments, at the member level, are total or partial. Declarant Demographics are presented.

Abstract: A system and method for estimating the popularity of song by calculating the (absolute and/or contrastive) harmonic surprise of each song in a corpus of music data, determining the popularity of each song in the corpus (e.g., based on a music chart, downloads, online streams), determining correlations between harmonic surprise and popularity, and estimating the popularity of an individual song based on the (absolute and/or contrastive) harmonic surprise of the individual song and the correlations between harmonic surprise and popularity.

Abstract: A method, computer system, and computer program product for determining and displaying tones with messaging information are provided. The embodiment may include receiving a plurality of user-entered messaging information from a messaging application. The embodiment may also include determining a tone associated with the plurality of received user-entered messaging information. The embodiment may further include determining whether a word, a phrase, or an image in the plurality of user-entered messaging information is used above a pre-configured threshold number of times by the user. The embodiment may also include determining a color and an animation for the determined tone based on a preconfigured mapping of a plurality of colors and a plurality of animations with a plurality of tones.

Abstract: The present invention provides a method and system for identifying, retrieving and presenting electronic documents responsive to user queries. The three distinct inventive concepts are relevancy ranking of responsive documents based on component query technique; cross-lingual searching; and search expansion using analytics of initial results to derive and generate a modified query. Each of these inventions enhances document search and retrieval systems and the three solutions may be used separately or in any combination. The three inventions apply in layers above an underlying search system, controlling the submission of requests to the underlying system in support of received search requests, typically originating with an end user. Invention (III) provides a semantic-expansion capability specifically utilizing the availability of language independent fields in the data being searched with natural language query terms. This invention is enhanced by incorporating the preceding two inventions.

Abstract: Embodiments are directed to a system, computer program product, and method for application of cognitive processing to a communication, and selectively transmitting the communication based on the cognitive processing. Natural language understanding (NLU) decomposes the communication to identify content and keywords. A dictionary determined to be contextually related to the communication is identified to support and enable a multi-dimensional analysis of the communication content. The communication is subject to dynamic filtering with support of the dictionary and dictionary content. A response is generated from the filtering, and is subject to selective transmission.

Abstract: Provided is a method and system for detecting a graph-based event in a social network, the method including generating a keyword graph based on social data collected from a social network system; separating the keyword graph into a plurality of candidate graphs through clustering; calculating a user interest for each of the plurality of candidate graphs based on a per-time variation of a social action associated with the social data; and determining k candidate graphs from among the plurality of candidate graphs as an event graph based on the user interest. Here, k denotes a natural number.

Abstract: A system receives a phrase that includes at least one tagged object and generates instantiated phrases by instantiations of each tagged object in the phrase. The system generates lists of natural language phrases by corresponding paraphrases of each of the instantiated phrases. The system generates ordered lists of natural language phrases by ordering natural language phrases in each list of natural language phrases based on occurrences of each natural language phrase. The system generates annotated natural language phrases by using each tagged object in the phrase to annotate the ordered lists of natural language phrases or an enhanced set of natural language phrases that is based on the ordered lists of natural language phrases.

Abstract: Mechanisms are provided for latent ambiguity handling in natural language processing. The method may include: providing an annotated semantic graph based on a knowledge base in which nodes representing semantic concepts are linked by semantic relationships, wherein one or more nodes are annotated to indicate a latent ambiguity of the semantic concept; processing a natural language input by activation of the annotated semantic graph; during processing when encountering an annotated node indicating a latent ambiguity of the semantic concept, applying a pre-defined latent ambiguity process to the node; and replacing any annotated nodes indicating a latent ambiguity of the concept remaining in an output of the processing of the natural language input with an alternative node from the semantic graph.

Abstract: The invention provides a method and system for automatically detecting semantic errors in a text. In order to detect the semantic errors in the text, the method generates a first set of features and a second set of features corresponding to each word in the text. A first set of features corresponds to statistical features of a word and a second set of features for a word corresponds to the features generated for a plurality of words surrounding the word in the text using matrix factorization techniques. The method, then, combines a first set of features and a second set of features to generate a third set of features corresponding to each word in the text. Thereafter, the method utilizes an Artificial Neural Network (ANN) model to detect semantic validity of each word based on a corresponding third set of features.

Abstract: Metadata for highlights of audiovisual content depicting a sporting event or other event are extracted from audiovisual content. The highlights may be segments of the content, such as a broadcast of a sporting event, that are of particular interest. Audio data for the audiovisual content is stored, and portions of the audio data indicating crowd excitement (noise) is automatically identified by analyzing an audio signal in the joint time and frequency domains. Multiple indicators are derived and subsequently processed to detect, validate, and render occurrences of crowd noise. Metadata are automatically generated, including time of occurrence, level of noise (excitement), and duration of cheering. Metadata may be stored, comprising at least a time index indicating a time, within the audiovisual content, at which each of the portions occurs. Periods of intense crowd noise may be used to identify highlights and/or to indicate crowd excitement during viewing of a highlight.

Abstract: Voice command matching during testing of voice-assisted application prototypes for languages with non-phonetic alphabets is described. A visual page of an application prototype is displayed during a testing phase of the application prototype. A speech-to-text service converts a non-phonetic voice command spoken in a language with a non-phonetic alphabet, captured by at least one microphone during the testing phase of the application prototype, into a non-phonetic text string in the non-phonetic alphabet of the voice command. A phonetic language translator translates the non-phonetic text string of the voice command into a phonetic text string in a phonetic alphabet of the voice command. A comparison module compares the phonetic text string of the voice command to phonetic text strings in the phonetic alphabet of stored voice commands associated with the application prototype to identify a matching voice command. A performance module performs an action associated with the matching voice command.

Abstract: Example implementations disclosed herein can be used to generate composite network policy graphs based on multiple network policy graphs input by network users that may have different goals for the network. The resulting composite network policy graph can be used to program a network so that it meets the requirements necessary to achieve the goals of at least some of the network users. In one example implementation, a method can include receiving multiple network policy graphs, generating composite endpoint groups based on relationships between endpoint groups and policy graph sources, generating composite paths based on the relationships between the endpoints and the network policy graphs, generating a composite network policy graph based on the composite endpoint groups and the composite paths, and analyzing the composite network policy graph to determine conflicts or errors.

Abstract: A system and method for a text search of a database. A text search expression is converted to a query plan having multiple search tokens. A one-pass indexing of an invested word index filters the inverted word index based on a search condition and identifies the applicable documents having the multiple search tokens.

Abstract: A database testing system may generate, based on a randomization process, test data for a database. The system may generate a query that, when processed by the database, produces a first result that comprises the row. The system may modify the query based on a randomization process and in view of the semantic properties of the query language associated with the queries. The system may predict the outcome of the modifies query based on the semantic properties and on the generated test data. The system may verify that the modified query, when processed by the database, produces results consistent with the prediction.

Abstract: According to one embodiment, there is provided an information display apparatus including a processor, the processor being configured to: designate a character string in a text displayed in a display unit in accordance with a user operation; determine whether a keyword is included in a part of the designated character string; generate, if it is determined that the keyword is included in the part of the designated character string, problem setting data based on the keyword included in the designated character string; and transmit the problem setting data to an external terminal.

Abstract: Disclosed are techniques for generating a language model that is applicable to the interpretation of commands for invoking application-based actions via a digital assistant device. In various embodiments, command templates that are each mapped to one of a plurality of action datasets are obtained to generate synthetic documents of a language model document corpus. Each synthetic document can be modified to include a tag that corresponds to an associated command template from which the document's generation was based. The language model can include a plurality of document clusters that are generated based on the modified synthetic documents, among other things.

Abstract: A system and method for automatically generating a narrative story receives data and information pertaining to a domain event. The received data and information and/or one or more derived features are then used to identify a plurality of angles for the narrative story. The plurality of angles is then filtered, for example through use of parameters that specify a focus for the narrative story, length of the narrative story, etc. Points associated with the filtered plurality of angles are then assembled and the narrative story is rendered using the filtered plurality of angles and the assembled points.

Abstract: A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process including generating index information regarding a first string data including a plurality of words or phrases, the index information indicating appearance positions of each of characters, setting flag information to the index information, the flag information indicating head positions plurality of words or phrases and end positions of each of the plurality of words or phrases, and extracting, from a second string data, a plurality of dividable words or phrases corresponding to the plurality of words or phrases by using the index information to which the flag information is set.

Abstract: Textual responses to open-ended (i.e., free-response) items provided by participants (e.g., by means of mobile wireless devices) are automatically classified, enabling an instructor to assess the responses in a convenient, organized fashion and adjust instruction accordingly.

Abstract: In an embodiment, the disclosed technologies are capable of identifying a target word within a text sequence; displaying a subset of candidate synonyms for the target word, determining a synonym selected from the subset of candidate synonyms, and replacing the target word with the selected synonym, where the subset of candidate synonyms has been created using syntactic dependency data for the target word.

Abstract: In some examples, a system for executing natural language processing techniques can include a processor to detect text comprising a word and a number. The processor can also embed, via a word embedding model, the word into a first vector of a vector space and embed the number by converting the number into a second vector of the vector space. Additionally, the processor can train a deep neural network to execute instructions based on the first embedded vector of the word and the second embedded vector of the number. Furthermore, the processor can process an instruction based on the trained deep neural network.

Abstract: Methods, apparatus, systems and articles of manufacture are disclosed to improve feature engineering efficiency. An example method disclosed herein includes retrieving a log file in a first file format, the log file containing feature occurrence data, generating a first unit operation based on the first file format to extract the feature occurrence data from the log file to a string, the first unit operation associated with a first metadata tag, generating second unit operations to identify respective features from the feature occurrence data, the second unit operations associated with respective second metadata tags, and generating a first sequence of the first metadata tag and the second metadata tags to create a first vector output file of the feature occurrence data.

Abstract: In an approach to parsing and analyzing contracts, one or more computer processors receive a policy agreement. The one or more computer processors parse the policy agreement for terms. The one or more computer processors compile a list of items associated with the terms in the policy agreement. The one or more computer processors associate each item of the list of items with one or more categories, wherein each category of the one or more categories defines an extent of coverage for each item. The one or more computer processors determine whether an item of a user is present in the list of items associated with the one or more terms in the policy agreement. The one or more computer processors determine the categories associated with the item. The one or more computer processors determine the extent of coverage for the item of the user based on the determined categories.

Abstract: An electronic device for providing a predictive word to a user, and an operating method therefor are provided. The electronic device includes a display, a processor, and a memory. The memory stores instructions that, when executed, cause the processor to display a user interface including a text input area and a keyboard, on the display, receive a first input through the keyboard, the first input including a part of a word, predict at least one word on the basis of at least a portion of the part of the word in response to the first input, the at least one word including a length in a selected range, display the at least one word on the display, receive a second input for selecting one word among the at least one word through the display, and allow the selected word to be displayed on the text input area.

Abstract: A syntax analysis method and apparatus are disclosed. The method includes: obtaining a source language sentence that is a translation of a target language sentence (S110); determining instances of state transition for the target language sentence according to the source language sentence and a correspondence between words of the target language sentence and words of the source language sentence (S120); and generating a syntax tree of the target language sentence according to the instances of state transition for the target language sentence (S130). The syntax analysis method and apparatus can improve efficiency of syntax analysis.

Abstract: A translation method and apparatus may respectively perform or include: using one or more processors, plural different translation processes, in parallel, for a source sentence in a first language, including encoding, to generate respective feature vectors, the source sentence in each of two or more translation processes of the plural translation processes or the source sentence and a variation of the source sentence in respective translation processes of the plural translation processes, and decoding each of the respective feature vectors to generate respective plural candidate sentences in a second language; and selecting a final sentence in the second language from the respective plural candidate sentences in the second language.

Abstract: Systems and methods are described for facilitating non-verbal communication. An electronic processor receives data from the hand-gesture sensor indicative of one or more gestures performed by a user, determines at least one word or phrase corresponding to the data from the hand-gestures sensor, and outputs a text representation of the at least one word or phrase on the display screen. Some systems output the text representation as a natural language sentence based on the data from the hand-gesture sensor and linguistic prosody information determined based, at least in part, on image data of the user captured while performing the one or more gesture. Some systems also includes at least one brain sensor and generate an alternative natural language text sentence in response to detecting a signal from the brain sensor indicative of a contradiction response after displaying the natural language text sentence on the display screen.

Abstract: Various embodiments of the present disclosure set forth a computer-implemented method for integrating an interactive virtual assistant in a meeting environment. The method comprises receiving an invitation to participate in the meeting environment, where the invitation includes text information, and applying at least a subset of a plurality of parsers to the text information in a given order to generate a text match for each of a plurality of fields of meeting information. The method further comprises, in response, when the text matches for at least a subset of the plurality of fields of meeting information meet one or more predetermined threshold criteria, causing the interactive virtual assistant to join the meeting environment based on the text matches for the at least the subset of the plurality of fields of meeting information.

Abstract: Embodiments of the present invention address deficiencies of the art in respect to conversation protocol validation and provide a method, system and computer program product for testing protocol compatibility between trading partners in a B2B conversation. In one embodiment of the invention, a method for testing protocol compatibility between roles in a B2B conversation can be provided. The method can include selecting at least two roles from amongst global process models, constructing local protocols for each of the selected roles, generating a conversation protocol from the constructed local protocols, and detecting dead-end states in the generated conversation protocol to identify protocol incompatibility while identifying protocol compatibility in the absence of dead-end states in the generated conversation protocol.

Abstract: A search and retrieval data processing system for retrieving classified data for execution against a cyber-security logic rules includes one or more hardware processors and memory, networked to communicably couple through a secure connection to a classified data database, the classified data database including an aggregated plurality of classified data records captured from a plurality of classified data sources; and the memory in communication with the processor, the memory storing an execution environment and the execution environment including an input port for receiving, from an entity, data associated with requested operations; a search engine for searching the classified data records of the classified database; and a logic execution module.

Abstract: This disclosure provides an apparatus and method for intelligent data access using latent semantic analysis and topic modeling. A method includes receiving, by a semantic query processing engine, a set of operator logbooks that include computer-readable text, receiving a natural language query, performing latent semantic analysis on the set of operator logbooks that include computer-readable text and the natural language query, and generating an ordered list of operator logbooks from the set of operator logbooks that include computer-readable text, wherein the ordered list of operator logbooks is ordered by relevance to the natural language query as determined using the latent semantic analysis.

Abstract: The present disclosure involves systems, software, and computer implemented methods for personalizing interactions within a conversational interface based on an input context. One example system performs operations including receiving a conversational input via a conversational interface associated with a particular user profile. The input is analyzed via a natural language processing engine to determine an intent and a personality input type. A persona response type associated with the determined personality input type is identified, and responsive content is determined. A particular persona associated with the particular user profile based on a related set of social network activity information associated with the user profile and that corresponds to the identified persona response type is identified.

Abstract: Methods for generating jokes include coupling server(s) with database(s) having words stored therein; receiving text at the server(s) from an external source communicatively coupled with the server(s) through a telecommunications network; in response to receiving the text at the server(s): selecting one or more topic keywords of the topic sentence using the server(s); generating one or more punch words with the server(s) using words stored in the database related to the topic keyword(s); adding bridges to the punch word(s), using the server(s), to generate one or more jokes; communicating a signal to a first computing device through the telecommunications network using the server(s); and in response to receiving the signal at the first computing device, displaying or speaking the joke(s) using the first computing device. Systems for generating jokes include networked computer components configured to carry out the methods. The methods/systems may also be used for recognizing jokes.

Abstract: One or more computing devices, systems, and/or methods for publishing message conversations to electronic forums are provided. For example, a message conversation between users may be identified. A request to publish the message conversation to an electronic forum may be received. The message conversation may be processed to create a first conversation summary of the message conversation. The message conversation may be evaluated to create a title. A forum discussion comprising the title and a first post of the first conversation summary is created. The forum discussion is published to an electronic forum.

Abstract: An apparatus comprising a memory and a processor configured for semi-autonomous natural language processing domain adaptation related activities. The processor coupled to the memory and configured to identify a corpus of documents of an evaluation domain and generate a first lexicon based on the corpus of documents of the evaluation domain, and determine a threshold that indicates a sufficiency of domain adaptation of the evaluation domain based at least in part on the first lexicon. The processor is further configured to identify a corpus of documents of a client domain, generate a second lexicon based on the corpus of documents of the client domain, determine a metric associated with the corpus of documents of the client domain and the second lexicon, and determine that domain adaptation of the client domain is complete when the metric exceeds the threshold.