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: A method and a device are provided for generating a summary of a hospital stay by a patient, including maintaining a database of electronic medical records (EMRs) where the EMRs include clinical notes pertaining to a patient during a time interval, identifying a set of significant physician notes for the time interval, generating a candidate set of summaries for each of the significant physician notes, for each significant physician note, analyzing the factuality of each of the candidate summaries and selecting the most factual summary, and generating a daily section for inclusion in a hospital course section of a discharge note that includes the selected factual summary for each of the significant physician notes.

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.

Abstract: Provided are systems, methods, and computer program products for searching a plurality of documents based on a text string. The system includes at least one processor programmed or configured to identify a plurality of documents including a plurality of document types, each document of the plurality of documents including a document type, receive a text string based on user input, generate, with a machine-learning model, an ordered list of document types based the text string, search the plurality of documents for the text string to identify a subset of documents based on similarity between the text string and each document of the subset of documents, rank the subset of documents based at least partially on the similarity, a document type of each document of the subset of documents, and the ordered list of document types, and generate a graphical user interface based on the ranked list of documents.

Abstract: A crime type inference system based on text data, may include: a keywords dictionary construction unit configured to receive crime source data, and generate a crime type keywords dictionary by extracting crime keywords; a data set construction unit configured to generate a dataset for crime type learning by using the crime source data and the keywords dictionary; a crime type prediction model training unit configured to generate a crime type prediction model by using the dataset, and train the crime type prediction model; and a crime type inference unit configured to infer a crime type by using new crime data.

Abstract: In one example, a method being performed by a computer system comprises: receiving an image file containing a pathology report; performing an image recognition operation on the image file to extract input text strings; detecting, using a natural language processing (NLP) model, entities from the input text strings, each entity including a label and a value; extracting, using the NLP model, the values of the entities from the input text strings; converting, based on a mapping table that maps entities and values to pre-determined terminologies, the values of at least some of the entities to the corresponding pre-determined terminologies; and generating a post-processed pathology report including the entities detected from the input text strings and the corresponding pre-determined terminologies.

Abstract: A system and method for enhancing e-commerce product listings is disclosed, performed on a server. The method involves importing listing data through Application Programming Interface (API) connections and analyzing this data to calculate a multimodal vector embedding. A quality score is estimated based on the embedding and real-time market data metrics. The method generates content elements, including product images, textual descriptions, and infographics, by applying a controlled generation algorithm through a text-to-image diffusion model. This model integrates loss-guidance and attention injection mechanisms to produce a controlled layout of the product images, producing content that is visually appealing and market-relevant. The resulting content elements are stored in the server's data storage, ready for e-commerce display.

Abstract: Aspects of the subject disclosure may include, for example, identifying an entity of a natural language question, locating a node of a knowledge graph corresponding to the entity, and generating a candidate answer set including a group of other entities located a predetermined proximity to the node. Contextual information for the group of other entities is determined from the knowledge graph, and the natural language question and contextual information are separately encoded to obtain separate encoded vectorial representations of the natural language question and members of the candidate answer set. The encoding uses pre-trained language model embeddings obtained via a bidirectional encoder representations from transformer encoding process. The encoded vectorial representations of the question under an influence of aspects of the contextual information are scored and a member of the candidate answer set selected according to the score to obtain an answer to the original question.

Abstract: The present disclosure provides a neural document embedding based ontology mapping. Conventional methods that map ontology concepts across domains/species extensively take help of bridging ontologies. Initially the system receives a Human Phenotype (HP) Identification number (ID) pertaining to a phenotype. A first HP ID vector is computed from the HP ID using a trained word2vec model. A second HP ID vector is computed from the HP ID using a trained Doc2vec model. An average HP ID vector is computed based on the first HP ID vector and the second HP ID vector. A plurality of cosine similarity scores are computed based on a comparison between the average HP ID vector and a plurality of average MP ID vectors. The plurality of MP IDs are sorted based on the plurality of cosine similarity scores. The plurality of MP IDs corresponding to the HP ID are selected based on a selection threshold.

Abstract: In an embodiment, a programmed computer system implemented via client-server Software as a Service (SaaS) techniques provides an interactive user interface for identifying specific portions of a digital document susceptible for review and improvement. A server computer may receive a representation of a digital document, such as an email, comprising words arranged into sentences. An embodiment may tokenize a set of all sentences comprising the sequence of sentences into a document-specific vocabulary, then compute a corresponding first and second score for each sentence of the sequence of sentences. The first score may represent a calculated probability of semantic importance of the corresponding sentence to an overall meaning of the digital document. The second score may represent a calculated likelihood that the corresponding sentence will be read by a future reader of the digital document. An embodiment may identify key sentences using the first scores and second scores.

Abstract: In an example embodiment, machine learning techniques are utilized to create virtual tables that connect to actual tables in a user's own system. The virtual table predicts how the user's data can be used to populate fields in newer versions of software that the user already runs, even when those fields are not present in the version that the user already runs. These tables may then be used in a specialized tool, which displays in one area of the display a screen of the version of the software that the user is currently running (“the existing version”) and displays in another area of the display a screen of the version of the software that the user is comparing to the existing version. Both display areas display the same screen, as rendered by their respective different versions of the software, using the same underlying base data.

Abstract: Examples described herein generate training data for machine learning (ML) for natural language (NL) processing (such as semantic parsing for translating NL). A formula tree is generated based on sampling both a formula grammar and NL templates. Using the formula tree, an ML training data instance pair is generated comprising a formula example and an NL example. A context example may also be used during instantiation of the formula tree. An ML model is trained with training data including the ML training data instance pair, and ML output is generated from NL input. The ML output includes, for example, a machine-interpretable formula, a database querying language command, or a general programming language instruction. Some examples support context-free grammar, probabilistic context-free grammar, and/or non-context-free production rules.

Abstract: A method comprising a deep learning based translation system translating a source sentence from language A to a target sentence in language B, placing constraints on the target sentence in language B.

Abstract: A classification system is provided that separates unclassified pages into unclassified, separated documents and classifies the separated documents. The classification system applies a page-level recognition model to the unclassified pages to recognize the logical boundaries between documents and, based on the logical boundaries, separates the pages into unclassified, separated documents. The classification system further applies a document-level recognition model to classify the separated documents.

Abstract: A system and method for document summarization generates summarized articles and risk factor categorizations for display at a graphical user interface (GUI) dashboard. A transaction monitoring system includes an adverse media dashboard pipeline for processing risk factor alerts and generating document summarizations for display at a user device. Document summarization extracts several sentences from a source text and stacks the sentences to create a summary. The method creates a vector representation of each sentence using a machine learning word embedding model and generates a sentence similarity matrix by computing cosine similarity values. A sentence graph creation algorithm creates a graph corresponding to the sentence similarity matrix and calculates importance scores used in selecting sentences for the document summary.

Abstract: A first set of text generation prompts may be determined based on an input document and a first text generation prompt template. The first set of text generation prompts may include an instruction to identify factual assertions in the input text. The prompts may be sent to a remote text generation modeling system, which may respond by identifying factual assertions in the input text. A second set of text generation prompts may be determined based on the factual assertions and a second text generation prompt template. The second set of text generation prompts may include an instruction to respond to the factual assertions. A response to the input text may be generated based on written responses provided by the remote text generation modeling system.

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for pre-training entity extraction models to facilitate domain adaptation in resource-constrained domains. In an example embodiment, a first machine learning model is used to encode sentences of a source domain corpus and a target domain corpus into sentence embeddings. The sentence embeddings of the target domain corpus are combined into a target corpus embedding. Training sentences from the source domain corpus within a threshold of similarity to the target corpus embedding are selected. A second machine learning model is trained on the training sentences selected from the source domain corpus.

Abstract: A method for automatically identifying word repetition errors includes the following steps: after performing word segmentation on a large-scale training corpus, performing statistics to obtain two-tuple and three-tuple structures including repeated words in the training corpus, and repeated combination degrees, left contextual adjacent word information entropy and right contextual adjacent word information entropy in the training corpus; performing statistics and recording words containing repeated characters in a Chinese dictionary and establishing a repeated word library of the Chinese dictionary; judging the repeated words appearing in the text to be subjected to error checking based on the repeated words in the Chinese dictionary; and judging the repeated words appearing in the text to be subjected to error checking based on the repeated combination degrees, left contextual adjacent word information entropy and right contextual adjacent word information entropy obtained by performing statistics.

Abstract: A system and method for machine learning classification of user sentiment is disclosed. The method includes storing including a plurality of category information. The plurality of category information includes a set of domain-specific category information. The method further includes extracting a plurality of aspects from textual data. The method further includes generating a sentiment by a machine learning model. The method further includes receiving the plurality of aspects and the set of domain-specific category information. The method further includes generating a sentiment based on the plurality of aspects and the set of domain-specific category information.

Abstract: A document to be analyzed and a set of key names to be extracted from the document are received. A set of strings of characters contained within the document and a location for each string of character are identified. Moreover, a document graph for the document is generated. The document graph includes a set of nodes and a set of edges. Each node of the set of nodes corresponds to a string of characters of the set of strings of characters. Each edge of the set of edges connects two or more nodes together. Additionally, based on the document graph and the received set of key names, a set of keys are identified. Furthermore, a set of values are extracted from the document, and a set of key-value pairs are generated based on the identified set of keys and the extracted set of values.

Abstract: An analysis platform combines unsupervised and semi-supervised approaches to quickly surface and organize relevant user intentions from conversational text (e.g., from natural language inputs). An unsupervised and semi-supervised pipeline is provided that integrates the fine-tuning of high performing language models via a language models fine-tuning module, a distributed KNN-graph building method via a KNN-graph building module, and community detection techniques for mining the intentions and topics from texts via an intention mining module.

Abstract: Various embodiments of the present disclosure provide methods, apparatus, systems, computing devices, computing entities, and/or the like for pre-processing dual-channel voice data for an automatic speech recognition mode. The method comprises creating one or more spectrograms for each channel of the dual-channel voice data by applying fast Fourier transform and generating power spectral density. The one or more balanced power spectrograms are created by merging the spectrograms of the channels, and are provided as input for acoustic and language processing by an automatic speech recognition machine learning model.

Abstract: A system for intelligent editing of legal documents. The system includes a computing device. The computing device is configured to access a plurality of legal source texts from a plurality of legal sources, generate a score for each of the plurality of legal source texts, train a natural language processing model as a function of the scored legal source texts and a first machine-learning process, receive user inputted legal text from a user device being operated by a human user to create a user legal document, analyze the user inputted legal text using the natural language processing model, suggest, as a function of the analyzing, a modification to a target text of the user inputted legal text, and generate a score for a modified user legal document. A method for intelligent editing of legal documents is also provided.

Abstract: A method for training large language models (LLMs) and using them for inference including training a base LLM, creating connected models while training the base LLM by coupling multiple trained base a parallel, series, or hybrid architecture, creating specialized connected language models for different specialized processing tasks by supplementally training two or more connected models different respective training sets, supplementally training a subset of connected language models by selectively routing one or more training data inputs to one or more specialized connected language models of the plurality of specialized connected language models responsive to at least one of accuracy optimization and task specialization, and routing prompts or derived prompts to the subset.

Abstract: This disclosure proposes systems and methods for entity resolution using speech recognition data. The system can receive audio data representing an utterance and perform automatic speech recognition (ASR) processing on the audio data to generate at least a first ASR data and a second ASR data. The system can perform natural language understanding (NLU) processing on the first ASR data to determine intent data and an indication of an entity. The system can determine a first portion of the first ASR data that corresponds to the indication of the entity. The system can determine a second portion of the second ASR data that corresponds to the indication of the entity without performing NLU on the second ASR data. The system can perform entity resolution (ER) on the second portion to identify a first entity.

Abstract: Certain aspects of the present disclosure provide techniques for orchestrating a user experience using natural language input. A user experience is orchestrated within an ecosystem of features for which a plurality of corresponding tokens is defined. Natural language describing a desired user experience result is received by a user experience orchestrator. A sequence of tokens corresponding to operations belonging to an ecosystem of features which produce a correct result for the natural language input can be identified by a trained large language model and executed by the user experience orchestrator using a token operator. The output operations determined by the model to produce or be likely to produce the correct result based on the natural language input can be disambiguated, confirmed, and/or executed.

Abstract: Methods and systems for estimation of a 3D hand pose are disclosed. A 2D image containing a detected hand is processed using a U-net network to obtain a global feature vector and a heatmap for the keypoints of the hand. Information from the global feature vector and the heatmap are concatenated to obtain a set of input tokens that are processed using a transformer encoder to obtain a first set of 2D keypoints representing estimated 2D locations of the keypoints in a first view. The first set of 2D keypoints are inputted as a query to a transformer decoder, to obtain a second set of 2D keypoints representing estimated 2D locations of the keypoints in a second view. The first and second sets of 2D keypoints are aggregated to output the set of estimated 3D keypoints.

Abstract: Systems and methods are described herein for processing negation in a natural language search query. The natural language search query is parsed to identify a plurality of portions of the natural language search query, and a first portion is determined to be a negation portion. A second portion to which the negation portion applies and a third portion to which the negation portion does not apply are then identified, and a content query is generated which includes a negation parameter corresponding to the second portion, and at least one other parameter corresponding to at least the third portion. Search results of the content query are then generated for output to the user.

Abstract: Interactive natural language processing (NLP) results may be generated that allow a user to interact with the NLP results but do so in an offline manner so that the documents being processed need not be stored online. To provide interactive NLP results, event handlers may be attached to elements of the NLP results. A user may then select a word or phrase of the NLP results to cause computer software provided with the NLP to present the interactive features. For example, a user may click on a definite noun phrase to view information for diagnosing antecedent basis errors. For another example, a user may click on a word to view information about how that word is used in a document, such as viewing portions of the document that include the word or variants of the word.

Abstract: A method executed by a computing device includes determining to update an entigen group within a knowledge database, where the entigen group includes a set of linked entigens that represent knowledge associated with an object. The method further includes determining a set of identigens for each word of a phrase associated with the object to produce sets of identigens. The method further includes interpreting the sets of identigens to determine a most likely meaning interpretation of the phrase and produce a new entigen group. The method further includes updating the entigen group utilizing the new entigen group to produce a curated entigen group such that a deficiency of the entigen group is resolved providing more accurate and more complete knowledge of the object.

Abstract: A support apparatus includes a generation apparatus and an analysis apparatus. The generation apparatus executes (a-1) to (a-5) with I=1 to n, and generates pieces of process information. The generation apparatus extracts material words from a document i in (a-1), extracts a treatment word i from the document i in (a-2), extracts a synthesis condition i from the document i in (a-3), extracts a characteristic value i related to a target material from the document i in (a-4), and associates the material words, the treatment word i, the synthesis condition i, and the characteristic value i with each other to generate process information i in (a-5). The analysis apparatus includes a combiner that generates composite process information including a common part common to the pieces of process information and different parts different among the pieces of process information, and an outputter that outputs the composite process information.

Abstract: A computer-implemented method, a computer program product, and a computer system for log anomaly detection. A computer receives a windowed log of incoming raw log messages. A computer compares statistical distribution metrics of entities in the windowed log with a statistical distribution extracted from a real-time statistical model for the entities. In response to the statistical distribution metrics being statistically different from the statistical distribution extracted from the real-time statistical model for the entities, a computer tags the windowed log as an entity anomaly. A computer computes a distance between an average word embedding vector in the windowed log and a statistical distribution extracted form a real-time statistical model for word embeddings. In response to the distance being greater than a predetermined threshold, a computer tags the windowed log as a word embedding anomaly. A computer sends to a user an alert with an anomaly severity level.

Abstract: Systems and method for processing domain specific claims is disclosed. The system comprises a memory, a processor, and a network interface communicatively coupled to the processor and the memory. The memory comprises computer instructions that when executed by the processor cause the system to perform functions. The functions comprise creating domain specific rules in a domain specific language based on domain specific regulations. The functions also comprise converting the created domain specific rules from the domain specific language to a target programming language. Further, the functions comprise accessing the domain specific claims via the network interface or a storage unit. Furthermore, the functions comprise validating the domain specific claims based on the converted domain specific rules respectively. In addition, the functions comprise providing a validation result corresponding to the domain specific claims respectively based on the validation.

Abstract: Conventionally, text summarization has been rule-based method and neural network based which required large dataset for training and the summary delivered had to be assessed by user in terms of relevancy. System and method are provided by present disclosure that generate causal insight summaries wherein event of importance is detected, and it is determined why event is relevant to a user. Text description is processed for named entities recognition, polarities of sentences identified, extraction of causal effects sentences (CES) and causal relationship identification in text segments which correspond to impacting events. Named entities are then role labeled. A score is computed for named entities, polarities of sentences, causal effects sentences, causal relationships, and the impacting events. A causal insight summary is generated with overall polarity being computed/determined.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for recognizing speech using a spiking neural network acoustic model implemented on a neuromorphic processor are described. In one aspect, a method includes receiving, a trained acoustic model implemented as a spiking neural network (SNN) on a neuromorphic processor of a client device, a set of feature coefficients that represent acoustic energy of input audio received from a microphone communicably coupled to the client device. The acoustic model is trained to predict speech sounds based on input feature coefficients. The acoustic model generates output data indicating predicted speech sounds corresponding to the set of feature coefficients that represent the input audio received from the microphone. The neuromorphic processor updates one or more parameters of the acoustic model using one or more learning rules and the predicted speech sounds of the output data.

Abstract: The deep semantic feature based few-shot intent recognition method for air traffic control instructions, belonging to the technical field of air traffic control; the method of the present invention solves technical problems in the prior art relating to incomplete and unreliable security situation awareness and semantic representation due to poor intent recognition ability for instructions with a small sample size, as well as difficulty in improving the applicability of models while keeping a small amount of labeled language information; the present invention uses the one obtained air traffic control instruction set to construct a domain language model and adopts an unsupervised learning method to enhance the mining and representation of deep-level features of air traffic control air-ground communication, thereby further improving the reliability of safety situation awareness and semantic representation.

Abstract: A computer-implemented method for generating natural language explanations of product formulations includes implementing a causal-based formulation network model within a web-based graphical, activating a target causal path of the causal-based formulation network model based on subscriber input; constructing a formulation impact explanation prompt based on a formulation outcome node and a sequence of interconnected formulation parameter nodes of the target causal path; generating, by a large language model, a natural language explanation of the target causal path based on an input of the formulation impact explanation prompt; and surfacing, by the web-based graphical user interface, the natural language explanation of the target casual path.

Abstract: Described are methods and systems are for generating dynamic conversational queries. For example, as opposed to being a simply reactive system, the methods and systems herein provide means for actively determining a user's intent and generating a dynamic query based on the determined user intent. Moreover, these methods and systems generate these queries in a conversational environment.

Abstract: Techniques and systems are described for performing semantic text searches. A semantic text-searching solution uses a machine learning system (such as a deep learning system) to determine associations between the semantic meanings of words. These associations are not limited by the spelling, syntax, grammar, or even definition of words. Instead, the associations can be based on the context in which characters, words, and/or phrases are used in relation to one another. In response to detecting a request to locate text within an electronic document associated with a keyword, the semantic text-searching solution can return strings within the document that have matching and/or related semantic meanings or contexts, in addition to exact matches (e.g., string matches) within the document. The semantic text-searching solution can then output an indication of the matching strings.