Abstract: A system and method are provided for generating a cybersecurity behavioral graph from a log files and/or other telemetry data, which can be unstructured or semi-structured data. The log files are applied to a machine learning (ML) model (e.g., a large language model (LLM)) that generates/extract from the log files entities and relationships between said entities. The entities and relationships can be constrained using a cybersecurity ontology or schema to ensure that the results are meaningful to a cybersecurity context. A graph is then generated by mapping the extracted entities to nodes in the graph and the relationships to edges connecting nodes. To more efficiently extract the entities and relationships from the data file, an LLM is used to generate regular expressions for the format of the log files. Once generated, the regular expressions can rapidly parse the log files to extract the entities and relationships.

Abstract: A visual dialogue method and system is provided. The method includes obtaining original input data, where the original input data includes current image data and a new question, and the new question is related to the current image data; preprocessing text data and image data in the original input data to obtain a text feature sequence and a visual feature sequence, respectively; using a VisDial dataset to construct a text corpus; obtaining text sequence knowledge by using a potential knowledge searcher based on the visual feature sequence and the text corpus; constructing a sparse scene graph based on the visual feature sequence; performing data fusion on the text feature sequence, the visual feature sequence, the text sequence knowledge, and the sparse scene graph to obtain a data fusion result; and obtaining dialogue content of the new question by using a decoder based on the data fusion result.

Abstract: A question answering system includes a dangerous operation determination unit configured to determine whether question-answer pair data includes a dangerous operation, and an answer sentence replacement unit configured to replace, when it is determined that the dangerous operation is included, an answer sentence including a description of the dangerous operation included in a document by a replaced answer sentence depending on a classification of the dangerous operation, to thereby create replaced question-answer pair data.

Abstract: A system for operating an autonomous agent with a remote operator includes a remote subsystem, a local subsystem, and a communication subsystem. A method for operating an autonomous agent with a remote operator includes receiving and processing a set of inputs; presenting a set of outputs to a remote subsystem; receiving an input from a remote operator; and operating the autonomous agent. Additionally or alternatively, the method can include any or all of: detecting a failure and/or triggering a failure response; detecting a particular scenario associated with the autonomous agent; triggering a remote operator request; processing remote operator input; and/or any other processes.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for music-aware speaker diarization. In an example embodiment, one or more audio classifiers detect speech and music independently of each other, which facilitates detecting regions in an audio track that contain music but do not contain speech. These music-only regions are compared to the transcript, and any transcription and speakers that overlap in time with the music-only regions are removed from the transcript. In some embodiments, rather than having the transcript display the text from this detected music, a visual representation of the audio waveform is included in the corresponding regions of the transcript.

Abstract: A computing system is disclosed that includes a processor and memory. The memory stores instructions that, when executed by the processor, cause the processor to perform several acts. The acts include generating a prompt that is to be input to a generative language model. The prompt includes conversational input set forth by a user. The acts further comprise providing the prompt as input to the generative language model, and receiving conversational output from the generative language model, where the generative language model generated the conversational output based upon the prompt. Additionally, the acts comprise streaming the conversational output on one of a SERP or webpage to which the user has navigated from the SERP.

Abstract: A method for generating control commands includes providing a document that includes at least one declaration that formulates a rule set, parsing the at least one declaration to generate a plurality of syntactical blocks, constructing terms and symbols from the syntactical blocks to generate a semantic representation, validating the semantic representation, and generating at least one control command based on the validated semantic representation, wherein the at least one control command corresponds to the rule set formulated by the at least one declaration. The at least one control command can advantageously be converted into a plurality of platform-specific instructions for driving a target platform. There is further defined a device for generating control commands and a corresponding system.

Abstract: Systems and methods for automatic evaluation of the quality of NLG outputs. In some aspects of the technology, a learned evaluation model may be pretrained first using NLG model pretraining tasks, and then with further pretraining tasks using automatically generated synthetic sentence pairs. In some cases, following pretraining, the evaluation model may be further fine-tuned using a set of human-graded sentence pairs, so that it learns to approximate the grades allocated by the human evaluators.

Abstract: Systems for use in data retrieval. A natural language processing module is used in conjunction with a classifier module to analyze and decompose a user query into its elements, and to determine a type of query. These modules are also used to determine the parameters for the query. The type of query and the parameters are then used to find a suitable function that creates a structured database query with the fields in the database query being populated using the parameters and query elements found by the NLP module. The completed structured database query is then used to retrieve relevant data records in response to the query. The retrieved records are then further processed and formatted as necessary to result in a suitable response to the query.

Abstract: A method for automatically classifying terms of a first ontology into categories of a classification scheme defined with respect to a second ontology includes generating, for each term in the first ontology and each term in the second ontology, an embedding encoding the term and a description of the term. The method further includes adding the generated embeddings to a transformer model and computing, for each pair of the embeddings consisting of a first term from the first ontology and a second term from the second ontology, a similarity metric quantifying a similarity of the first term and the second term. The method still further provides for determining a matching scheme based on the similarity metric computed with respect to each pair of the embeddings, where the matching scheme associates term of the first ontology with one or more relevant categories of the classification scheme defined with respect to the second ontology.

Abstract: A method includes obtaining a text document, generating a first mark-up of the text document by a first natural language processing (NLP) model, and displaying the text document and the first mark-up. The method also includes receiving a user interaction with a portion of the first mark-up. The portion of the first mark-up of the text document may be associated with a portion of the text document. The method additionally includes, based on the user interaction with the portion of the first mark-up, selecting a second NLP model by which to process the portion of the text document, where the second NLP model is different from the first NLP model. The method further includes, based on selecting the second NLP model, generating a second mark-up of the text document by processing at least the portion thereof by the second NLP model, and displaying the text document and the second mark-up.

Abstract: The present disclosure relates to systems and methods for automatic generation of summaries for record objects using one or more large language models. The system can identify a plurality of electronic activities matched to a record object of a customer relationship management system. The system can generate one or more text strings from the plurality of electronic activities using the large language models. The system can generate a first set of topics by inputting a first set of text strings into the large language models. The system can generate a second set of topics by inputting a first subset of text strings of the first set of text strings into the large language models. The system can transmit one or more topics to a computing device for presentation.

Abstract: A system for conducting parallelization of tasks is disclosed. The system includes an interface for receiving messages comprising a representation of logic describing two tasks to be executed in parallel, the message further comprising a content payload for use in the tasks. The system further includes a processor comprising devices running on independent machines, each device comprising a processing manager unit and at least two processing units. The processing manager is configured to parse the received messages and to distribute the at least two tasks to the at least two processing units for independent and parallel processing relative to the content payload.

Abstract: The disclosed embodiments include computer-implemented processes that generate adaptive textual explanations of output using trained artificial intelligence processes. For example, an apparatus may generate an input dataset based on elements of first interaction data associated with a first temporal interval, and based on an application of a trained artificial intelligence process to the input dataset, generate output data representative of a predicted likelihood of an occurrence of an event during a second temporal interval. Further, and based on an application of a trained explainability process to the input dataset, the apparatus may generate an element of textual content that characterizes an outcome associated with the predicted likelihood of the occurrence of the event, where the element of textual content is associated with a feature value of the input dataset. The apparatus may also transmit a portion of the output data and the element of textual content to a computing system.

Abstract: An information processing apparatus according to the present invention includes: an acceptance unit that accepts a process request to an operation system; a specifying unit that, based on the process request, specifies an operation task to be executed in the operation system; an extraction unit that performs text analysis on the process request and extracts an answer item corresponding to an input item required at execution of the operation task from the process request; and an execution unit that executes the operation task based on the answer item.

Abstract: Embodiments are provided for generating a reasonable language model learning for text data in a knowledge graph in a computing system by a processor. One or more data sources and one or more triples may be analyzed from a knowledge graph. Training data having one or more candidate labels associated with one or more of the triples may be generated. One or more reasonable language models may be trained based on the training data.

Abstract: In a method of responding based on sentence paraphrase recognition for dialog system, main keywords of a domain and patterns thereof are recognized and extracted based on a morpheme analysis result in a pre-processing process. Question domains/sub-categories/dialogue-acts are classified using the morpheme analysis result and the extracted main keywords and patterns. Learning a model is performed using classification features of the classified question domains, sub-categories, and dialogue-acts as semantic features of query sentences, and sentence semantic vectors are extracted by measuring similarity between the vectors. A language model of letters is trained and similarity in expression and structure is analyzed by extracting a sentence expression vector based on the letter.

Abstract: A document management system analyzes document clauses using document clause clusters. The document management system uses measures of similarity between document clauses from different documents to assign clauses to clause clusters. Clause clusters may be used to perform various analyses, such as to assign clauses a classification corresponding to a relevant clause cluster. The document management system provides analyses performed using document clause clusters for user review, such as to approve clause clusters, classify clause clusters, modify clause clusters, or some combination thereof.

Abstract: Systems and methods are provided that train a machine-learned language encoding model through the use of a contrastive learning task. In particular, the present disclosure describes a contrastive learning task where the encoder learns to distinguish input tokens from plausible alternatives. In some implementations, on each training example the proposed method masks out some subset (e.g., 15%) of the original input tokens, replaces the masked tokens with samples from a “generator” (e.g., which may be a small masked language model), and then trains the encoder to predict whether each token comes from the original data or is a replacement produced by the generator.

Abstract: A sentence generation device has: an estimation unit for receiving input of a first sentence and a focus point related to generation of a second sentence to be generated based on the first sentence, and estimating importance of each word constituting the first sentence using a pre-trained model; and a generation unit for generating the second sentence based on the importance, and thus makes it possible to evaluate importance of a constituent element of an input sentence in correspondence with a designated focus point.

Abstract: An entity recognition method, apparatus, electronic device, and computer-readable storage medium are provided. The method includes: determining at least one entity boundary word corresponding to a text sequence; determining at least one entity candidate region in the text sequence based on the at least one entity boundary word; and performing entity recognition on the text sequence and identifying at least one entity in the text sequence based on the at least one entity candidate region.

Abstract: A text processing method, a model training method, and an apparatus related to the field of artificial intelligence is provided. The method includes: obtaining target knowledge data; processing the target knowledge data to obtain a target knowledge vector; processing to-be-processed text to obtain a target text vector; fusing the target text vector and the target knowledge vector based on a target fusion model, to obtain a fused target text vector and a fused target knowledge vector; and processing the fused target text vector and/or the fused target knowledge vector based on a target processing model, to obtain a processing result corresponding to a target task. The foregoing technical solution can improve accuracy of a result of processing a target task by the target processing model.

Abstract: Systems, methods, and devices including smart interfaces with facilitated input and mistake recovery are described. For example, a smart interface system can identify one or more portions of user input as alterable decisions, and, for each of the one or more alterable decisions, store, in a memory, information about one or more alternative options for the alterable decision. The system can also identify one of the alterable decisions as the currently alterable decision, and upon receiving an input indicative of an actuation of the alteration key, alter the currently alterable decision to another of the one or more alternative options based on the stored information.

Abstract: Provided is a computer-implemented method, system, and computer program product for process mining asynchronous support conversations using attributed directly follows graphing. A processor may collect a plurality of conversation threads from an asynchronous data stream. The processor may label each utterance of a plurality of utterances from the plurality of conversation threads with an event label. The processor may analyze the event label for each utterance of the plurality of utterances. The processor may generate, based on the analyzing of the event label for each utterance, an attributed directly follows graph (DFG).

Abstract: An information processing method includes receiving first request information entered by a user, determining a first task engine for the first request information, where a first slot is set in the first task engine, extracting key information from the first request information based on the first slot, and if the key information fails to be extracted from the first request information based on the first slot, or if the key information is extracted from the first request information based on the first slot, but the extracted key information does not meet a condition, obtaining target key information from a shared parameter list of the user.

Abstract: A method executed by a computing device includes determining a set of identigens for each phrase word of a phrase to produce sets of identigens. A set of identigens of the sets of identigens represents one or more different meanings of a phrase word of the phrase. The method further includes obtaining sensor information for one or more phrase words of the phrase. The method further includes selecting an identigen of a first set of identigens based on the sensor information to produce a first identigen selection for the first set of identigens having a selected meaning of one or more different meanings of the first phrase word. The method further includes interpreting remaining sets of identigens of the sets of identigens to produce an entigen group so that the entigen group represents a most likely meaning interpretation of the phrase.

Abstract: A method, computer system, and a computer program for conducting a conversational search. In one embodiment, the method includes monitoring a dialogue involving at least one user and capturing user utterances provided during the dialogue. These user utterances are then analyzed and classified according to the context of the dialogue. The dialogue is intervened upon the determination that a user needs additional information and/or upon execution of an action on behalf of the user and based on the plurality of user utterances and context. The Required information may be provided back to the user using Documentation Recommendation Module. The Documentation Recommendation Module determines a valid resource recommendation as determined by a combination of the context and a resource that includes additional information.

Abstract: Described herein are systems and methods for generating a computing network from natural language descriptions of the computing network are provided. In one or more examples, the systems and methods described below can be used harvest publically available (or even privately available) natural language descriptions of a computing network, and convert those descriptions into an operational replica of the described computing network. By harvesting both publically available data, as well as other resources, the systems and methods described herein can allow for an analyst tasked with analyzing a given computing network to generate a fully operational replica of the computing network without having to have direct access to the network. In one or more examples, the analyst can recreate a fully-functional replica of the network to be analyzed based on partial descriptions of the computing network, thereby greatly improving the level of analysis capable of being performed.

Abstract: Provided is a method, a computer program product, and a system for associating mathematical functions to numerical text in a natural language sample. The method includes inputting a natural language sample from a text dataset and identifying a numerical text within the natural language sample. The method further includes displaying a mathematical function corresponding to the numerical text to be selected. The mathematical function can be selected via graphical user interface displayed on a computing device. The method also includes receiving and inserting the mathematical function as a feature into a feature vector of the natural language sample and selecting an output label for the natural language sample. The output label relates to the mathematical function selected for the numerical text. The method further includes exporting the natural language sample into a labeled dataset which can be used to train a machine learning model.

Abstract: When creators generate media content in accordance with media programs, the media content is evaluated to identify any number of violations of policies, and to generate scores representing a level of risk that the creators will violate one or more of the policies in the future. Subsequently, media content of the creators is transmitted to listeners in accordance with the scores. In addition to audio data of creators or transcripts of the audio data, scores may be generated based on images associated with the creators, titles or summaries of media programs, or reports received from listeners. Scores calculated for creators may increase or decrease over time, depending on numbers of violations of policies by such creators, or other factors, and be utilized with a goal of protecting listeners against exposure to harmful content.

Abstract: Methods, systems, and computer-readable media for interactive command generation for natural language input are disclosed. A natural language dialog system receives a natural language input for a dialog with a user. The system determines a state representation of the dialog based at least in part on the natural language input. The state representation indicates an operation offered by a service. The system generates a natural language output based at least in part on the natural language input. The natural language output solicits an additional natural language input for the dialog. The system determines an updated state representation of the dialog based at least in part on the additional natural language input and the state representation. The updated state representation indicates parameter value(s) for the operation. Based at least in part on the updated state representation, the system generates a command invoking the operation with the parameter value(s).

Abstract: A system, computer program product, and method are provided for jointly learning dictionary based rules and dictionary candidates. Natural language text is received and parsed into subsets, with the subset being subjected to natural language processing to identify one or more verbs within the subset. The identified verbs are evaluated with respect to a dictionary and one or more rules. The evaluation is directed at each predicate in the rules with respect to the identified verbs. A neural network is leveraged to jointly induce modification of the rules and one or more dictionaries responsive to the evaluation.

Abstract: A computer system includes memory configured to store a document database and a machine learning model. The document database includes multiple historical documents each having at least one version labeled as compliant and at least one version labeled as non-compliant. The system includes a creator user interface, a compliance user interface, an automated distribution module, and a model building module configured to train the machine learning model to classify a document according to a compliance score indicating a likelihood of document compliance with one or more compliance criteria. The system also includes an orchestrator module configured to receive the compliance score for the submitted document from the machine learning model, determine whether the compliance score is greater than or equal to a compliance score threshold, and supply the submitted document to the compliance user interface for transmission to the compliance team device when the compliance score is above a threshold.

Abstract: Text editing apparatus comprises a database memory configured to store a text database, in which the text database is configured to store a plurality of text portions and a set of links between text portions, the set of links defining a document as a linked list of the text portions; and a data processor configured, in response to user input, to perform an editing operation to edit the text database so as to define an edited document by changing at least one of: (i) text within a text portion and (ii) the set of links between text portions.

Abstract: In some embodiments, text for user consumption may be generated based on an intended user action category and a user profile. In some embodiments, an action category, a plurality of text seeds, and a profile comprising feature values may be obtained. Context values may be generated based on the feature values, and text generation models may be obtained based on the text seeds. In some embodiments, messages may be generated using the text generation models based on the action category and the context values. Weights associated with the messages may be determined, and a first text message of the messages may be sent to an address associated with the profile based on the weights. Based on a reaction value obtained in response to the first message, a first expected allocation value may be updated based on the reaction value.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for announcing and detecting automated conversation are disclosed. One of the methods includes initiating, over a natural language communication channel, a conversation with a communication participant using a natural language communication method that includes a dialogue of natural language communications. The communication participant is determined to be automated using a pre-defined adaptive interactive protocol that specifies natural language linguistic transformations defined in a sequence. The conversation can be transitioned to a communication method that is different form the natural language communication method in response to determining that the communication participant is automated.

Abstract: Portions of text data generated from inverse text normalization may be redacted. Text data for redaction may be obtained. One or more inverse text normalization models may be applied to the text data to generate normalized text data. A machine learning model, trained to recognize text for redaction, may be applied to identify portions of the normalized text data for redaction. The identified portions may be redacted and the redacted normalized text provided to a destination.

Abstract: An apparatus for generating obfuscated data within a computing environment, comprising a processor and a memory containing instructions configuring the processor to access a database containing a plurality of private data elements belonging to at least a private record, generate a set of obfuscated data elements, representative of the at least a private record, as a function of the plurality of private data elements using an generative model, determine a first distance measure between at least an obfuscated data element within the set of obfuscated data elements and at least a private data element of the plurality of private data elements within the database, and verify the first distance measure is within a distance range, wherein a minimum threshold of the distance range is determined as a function of a deidentification parameter and a maximum threshold of the distance range is determined as a function of an obfuscation parameter.

Abstract: Implementations relate to effectively localizing system responses, that include dynamic information, to target language(s), such that the system responses are grammatical and/or natural in the target language(s). Some of those implementations relate to various techniques for resource efficient generation of templates for a target language. Some versions of those implementations relate to resource efficient generation of target language natural language generation (NLG) templates and, more particularly, to techniques that enable a human user to generate a target language NLG template more efficiently and/or with greater accuracy. The more efficient target language NLG template generation enables less utilization of various client device resources and/or can mitigate the risk of flawed NLG templates being provided for live use in one or more systems.

Abstract: A computing system includes a processor and memory storing instructions that, when executed by the processor, cause the processor to perform acts. The acts include receiving a query provided by a user. The acts additionally include determining that the query is related to a comparison between entities. Based upon the determining that the query is related to the comparison between entities, the computing system generates a prompt that is to be input to a generative language model, where the prompt includes: 1) an instruction for the generative language model to generate a table based upon the query; and 2) attribute values for entities identified by a search system based upon the query. The acts also include providing the prompt as input to the generative language model, where the generative language model generates a table based upon the prompt, and further where the table includes the attribute values for the entities.

Abstract: An apparatus and method for classifying an entity datum into instruction sets is provided. The apparatus includes processor that may receive the entity data, which includes data describing entity operations and an assessment of operations of each entity. The processor may receive instruction sets including an impact datum describing an effect of a respective instruction set on the entity data and classify elements of data describing assessments into instruction sets. The processor uses a machine learning model including a classifier to correlate data describing the assessment with data describing instruction sets and to generate a user interface. The user interface configures a display device to display a sequence based on classification of elements of data describing assessments of respective instruction sets into at least some instruction sets. The sequence may change a color, or an order based on the impact datum relative to the entity data.

Abstract: Methods and systems for curating data by a data manager are disclosed. Data may be curated from various data sources before being provided to downstream consumers that may rely on the trustworthiness of the curated data in order to provide desired computer-implemented services. During the data curation process, data curation resources are used to improve the trustworthiness and/or value of the collected data. However, data curation resources (e.g., data curators, computing resources) may be limited and/or insufficient to perform the data curation process as desired, which may result in unusable and/or uncurated (e.g., untrustworthy) data. Thus, the data may be screened for ambiguous values. A potential replacement value for each ambiguous value may be provided to the data source and the data source may indicate whether the potential replacement value should be used in the data pipeline as a final replacement value for the ambiguous value.

Abstract: Techniques for detecting a fraudulent attempt by an adversarial user to voice verify as a user are presented. An authenticator component can determine characteristics of voice information received in connection with a user account based on analysis of the voice information. In response to determining the characteristics sufficiently match characteristics of a voice print associated with the user account, authenticator component can determine a similarity score based on comparing the characteristics of the voice information and other characteristics of a set of previously stored voice prints associated with the user account. Authenticator component can determine whether the similarity score is higher than a threshold similarity score to indicate whether the voice information is a replay of a recording or a deep fake emulation of the voice of the user. Above the threshold can indicate the voice information is fraudulent, and below the threshold can indicate the voice information is valid.

Abstract: A translating method using visually represented elements, and device therefor is provided.

Abstract: Processing stacked data structures is provided. A system receives an input audio signal detected by a sensor of a local computing device, identifies an acoustic signature, and identifies an account corresponding to the signature. The system establishes a session and a profile stack data structure including a first profile layer having policies configured by a third-party device. The system pushes, to the profile stack data structure, a second profile layer retrieved from the account. The system parses the input audio signal to identify a request and a trigger keyword. The system generates, based on the trigger keyword and the second profile layer, a first action data structure compatible with the first profile layer. The system provides the first action data structure for execution. The system disassembles the profile stack data structure to remove the first profile layer or the second profile layer from the profile stack data structure.

Abstract: A speech recognition system comprises: an input, for receiving an input signal from at least one microphone; a first buffer, for storing the input signal; a noise reduction block, for receiving the input signal and generating a noise reduced input signal; a speech recognition engine, for receiving either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block; and a selection circuit for directing either the input signal output from the first buffer or the noise reduced input signal from the noise reduction block to the speech recognition engine.

Abstract: The present invention discloses a transfer information determination method and device through deep learning, by which a determination is made on whether transfer information is included in a message, and the transfer information is classified. A method for determining transfer information within a message through natural language processing based on deep learning according to the present invention comprises the steps of: pre-processing an acquired message in a user terminal according to a reference word; extracting an embedding vector corresponding to each segmented text from the preprocessed message to determine whether transfer information is included, through weighted calculation of the extracted embedding vector; and classifying the transfer information within the pre-processed message determined to include the transfer information.

Abstract: Methods for correcting raw text generated by deep learning techniques is disclosed. The methods may be performed by systems/computing devices described herein. Raw text previously generated by the deep learning techniques may be obtained. A search query can be generated from a raw text sentence of the raw text. The search query is executed against a knowledge base or a corpus of text to obtain a set of search results, the set of search results comprising a plurality of candidate true sentences that can potentially be utilized to correct one or more entities or phrases of the raw text sentence. A candidate true sentence is selected from the plurality and used to correct the raw text sentence. For example, at least one entity or phrase of the candidate true sentence can be used to replace a corresponding entity or phrase of the raw text sentence.

Abstract: A natural language understanding (NLU) framework includes a modeling and optimization system that enables enhanced understanding and explainability to the operation of the NLU framework. The NLU framework includes a configuration vector storing settings of various components that may be applied during NLU inference of an utterance, such as which components should be activated or deactivated, as well as which numerical values (e.g., threshold values, coefficients, weight values) that are used by these components during operation. By using this configuration vector to systematically disable and adjust numerical parameters of the components of the NLU framework, and then determining the performance of the NLU framework in these configurations, the modeling and optimization system determines relationships between, as well as the relative importance of, the components of the NLU framework.

Abstract: Systems, apparatuses, methods, and computer program products are disclosed for automated prototyping of a topic model. An example method includes a data manipulation engine ingesting and pre-processing source data from a set of data sources, a feature extraction engine that thereafter transforms the pre-processed data into a set of numeric representations of the pre-processed data, and an autonomous model generator that automatically generates a trained topic model using the set of numeric representations. Embodiments further enable visualization of topic model output, which permits a user to easily consume and utilize information from a topic model for any number of purposes.