Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a generative neural network to convert conditioning text inputs to audio outputs. The generative neural network includes an alignment neural network that is configured to receive a generative input that includes the conditioning text input and to process the generative input to generate an aligned conditioning sequence that comprises a respective feature representation at each of a plurality of first time steps and that is temporally aligned with the audio output.

Abstract: Systems, methods, devices, and non-transitory, computer-readable storage media are disclosed for matching a service requester with a service provider via a taxonomy based directed graph. The method includes: receiving a keyword associated with a service; accessing a directed graph including a root node and nodes connected by edges, each node having a title; identifying a second node of the directed graph for each of service providers, each second node having a title matching a skill of a respective service provider; determining a distance between the first node and each second node along the directed graph; and ranking the service providers based at least in part on the distance between the first node and each second node. Systems, methods, devices, and non-transitory, computer-readable storage media are further disclosed for determining and storing a quality score for the revised linguistic content.

Abstract: Systems and processes for operating an intelligent automated assistant are provided. An example method includes, at an electronic device having one or more processors and memory, receiving an utterance including a user request, determining a natural language representation of the user request, determining a first software process associated with the natural language representation, determining whether the natural language representation can be executed by a task flow of the first software process, and in accordance with a determination that the natural language representation cannot be executed by the task flow of the first software process: determining a set of transformation instructions, determining a revised natural language representation using the set of transformation instructions, and providing the revised natural language representation to a second software process.

Abstract: A video game system provides dialog responses based on a natural language model (NLM). The NLM is a language model that receives a language input, such as a dialog selection, audio recording, or natural language text input provided by a user of the video game system. In response to the language input, and based on a corpus of natural language candidate lines, the NLM identifies one or more potential responses. The video game system selects a final response from the identified potential responses and provides the selected response to the user via, for example, one or more display frames or via an audio output.

Abstract: An apparatus and method for a machine learning engine for domain generalization which trains a vision transformer neural network using a training dataset including at least two domains for diagnosis of a medical condition. Image patches and class tokens are processed through a sequence of feature extraction transformer blocks to obtain a predicted class token. In parallel, intermediate class tokens are extracted as outputs of each of the feature extraction transformer blocks, where each transformer block is a sub-model. One sub-model is randomly sampled from the sub-models to obtain a sampled intermediate class token. The intermediate class token is used to make a sub-model prediction. The vision transformer neural network is optimized based on a difference between the predicted class token and the sub-model prediction. Inferencing is performed for a target medical image in a target domain that is different from the at least two domains.

Abstract: Systems and methods are disclosed for automatically extracting keys and corresponding values in any type of source document. Extracting desired words from the tokens in any type of document is based on a uniform approach to represent the source document. This uniform representation encodes features of the desired tokens along with the neighborhood information so that values associated with a given key can be extracted. The disclosed technique learns the representation of tokens independent of source document type and the learned representation is then used to determine relationships between multiple tokens. The neighborhood information and position information are used to determine various relationships between keys and values.

Abstract: A model training method, a model training platform, an electronic device and a storage medium are provided, which can be used in the field of artificial intelligence, particularly the fields of natural language processing and deep learning. The model training method includes: receiving an input; determining, based on the input, a user-oriented prefabricated function; determining, based on the input, a model training function; determining, based on the input, a pre-trained model; determining, based on the input, a network structure associated with the pre-trained model so as to support use of the pre-trained model; training, based on the input, the model by using the prefabricated function, the model training function, and the pre-trained model; and providing an output associated with a trained model.

Abstract: A method of training a model, a method of determining a word vector, a device, a medium, and a product are provided, which may be applied to fields of natural language processing, information processing, etc. The method includes: acquiring a first word vector set corresponding to a first word set; and generating a reduced-dimensional word vector for each word vector in the first word vector set based on a word embedding model, generating, for other word vector in the first word vector set, a first probability distribution in the first word vector set based on the reduced-dimensional word vector, and adjusting a parameter of the word embedding model so as to minimize a difference between the first probability distribution and a second probability distribution for the other word vector determined by a number of word vector in the first word vector set.

Abstract: In a data lake, a control data object is defined. The control object defines the processes and relationships of processes associated with a data set in the data lake. The control has states that are tied to and adapt in response to state changes of the associated data set. A control can have a control type. The system automatically carries forward enabled processes from one data set version to the next data set version. The system uses the control definition to execute processes, such as compaction or data quality scans, on data sets in the data lake.

Abstract: This disclosure improves computer functionality by enabling various hierarchies of chatbot application programs operative based on data structures containing unstructured texts. Therefore, such hierarchies enable some chatbot application programs to manage other chatbot application programs, which improves virtual assistance, reduces programming efforts, customizes output by user types, and enhances process management.

Abstract: A computer-implemented system includes identifying a target hierarchical taxonomy comprising a plurality of distinct hierarchical taxonomy categories; extracting a plurality of distinct taxonomy tokens from the plurality of distinct hierarchical taxonomy categories; computing a taxonomy vector corpus based on the plurality of distinct taxonomy tokens; computing a plurality of distinct taxonomy clusters based on an input of the taxonomy vector corpus; constructing a hierarchical taxonomy classifier based on the plurality of distinct taxonomy clusters; converting a volume of unlabeled structured datasets to a plurality of distinct corpora of taxonomy-labeled structured datasets based on the hierarchical taxonomy classifier; and outputting at least one corpus of taxonomy-labeled structured datasets of the plurality of distinct corpora of taxonomy-labeled structured datasets based on an input of a data classification query.

Abstract: A method of training a ranking model, and an electronic device, which relate to technical fields of natural language processing and intelligent search. The method includes: in training the ranking model, firstly acquiring a plurality of first sample pairs and respective label information; for each first sample pair, inputting a first search text, a first title text of a first candidate text, and a first target summary corresponding to the first candidate text into an initial language model to obtain a second relevance score corresponding to the each first sample pair; then using the first target summary to replace the first candidate text to participate in the training of the ranking model, and updating at least one network parameter of the initial language model according to the label information and the second relevance score corresponding to each first sample pair.

Abstract: Implementations relate to managing multimedia content that is obtained by large language model(s) (LLM(s)) and/or generated by other generative model(s). Processor(s) of a system can: receive natural language (NL) based input that requests multimedia content, generate a response that is responsive to the NL based input, and cause the response to be rendered. In some implementations, and in generating the response, the processor(s) can process, using a LLM, LLM input to generate LLM output, and determine, based on the LLM output, at least multimedia content to be included in the response. Further, the processor(s) can evaluate the multimedia content to determine whether it should be included in the response. In response to determining that the multimedia content should not be included in the response, the processor(s) can cause the response, including alternative multimedia content or other textual content, to be rendered.

Abstract: A hybrid Hidden Markov Model (HMM) and Machine Learning (ML) systems and apparatus for classification in the case of data instances with imbalanced class distribution, including a Hidden Markov Model for generating a log-likelihood score for each data instance. Implementations of the hybrid system and method detect fraudulent activity and classifies documents with accuracy that surpasses conventional classifiers. In one implementation, Hidden Markov Model (HMM) for generating a log-likelihood score based on an attribute value vector for a set of keyword features characterizing a Web page. In one implementation, the HMM generates a log-likelihood score based on an attribute value vector for page layout characterizing a document image. Resulting attribute value vectors are ranked and divided into bins grouped by log-likelihood scores within equal ranges. Various machine learning models are trained using the balanced vectors obtained by accumulating from all the bins of vectors.

Abstract: Provided are a text duplicate checking method, an electronic device and a computer-readable storage medium. The method includes storing a fingerprint set and a corresponding text ID in a byte data manner to obtain a fingerprint library; acquiring a target text and creating a target fingerprint; obtaining a comparison fingerprint set from map memories according to the target fingerprint, and calculating a similarity between the target fingerprint and each comparison fingerprint in the comparison fingerprint set separately; and based on a determination result that a number of 1s in binary values of one similarity is less than or equal to a preset value, querying a text ID corresponding to the one similarity, to implement duplicate checking of the target text.

Abstract: A schema and cell value aware Named Entity Recognition (NER) model is used to perform natural language queries. Natural language queries may be received via an interface of a natural language query processing system. A fuzzy search may be performed that allows non-exact matches for column names or cell values of data sets potentially used to answer the natural language query. An NER model that adds a type embedding for an exact match of a column name or cell found in the fuzzy search that corresponds to a span of one or more words may be applied as part of generating the entity prediction for the natural language query. One or more queries to at least one of the data sets may be performed to return a result to the natural language query using the entity prediction generated by the NER machine learning model.

Abstract: To provide enhanced search capabilities in a process control system, a knowledge repository is generated that includes both contextual data and time series data. The contextual data organizes process plant-related data according to semantic relations between the process plant-related data and the process plant entities. When a user submits a process plant search query related to process plant entities within a process plant, search results are obtained by identifying a data set from the knowledge repository. The contextual data categorizes process parameters so that users can search for a particular process parameter category. Users can tag previous searches to execute them once again at a later time.

Abstract: A method of extracting and displaying postural measurements from patient data includes retrieving, by a processor of a computing device, the patient data from memory. The patient data includes a geometric mesh representation of a patient, including a plurality of data points corresponding to spatial coordinates of a plurality of vertices in three dimensions. The method also includes determining, by the processor, a reference geometry along the geometric mesh representation in a fixed position with respect to the spatial coordinates; determining, by the processor, a landmark corresponding to one of skeletal or soft tissue anatomy for the patient; and determining, by the processor, a postural deviation of a body portion of the patient by comparing the reference geometry and the landmark. The method further includes displaying, by a display of the computing device, a graphical user interface indicating a characteristic related to the postural deviation.

Abstract: A method includes: receiving a user query; generating first embedding data for the user query via a language agnostic machine learning embedding model; and predicting a first intent of the user query based on the first embedding data.

Abstract: Sentiment capture by wireless network elements is provided herein. A method can include extracting, by a system comprising a processor, features of sensor data captured by a sensor, communicatively coupled to the system via a wireless communication network and located in an area, wherein the sensor data is representative of respective persons present in the area, resulting in extracted features; determining, by the system, sentiment data, representative of an emotional condition of the respective persons present in the area, by correlating the extracted features to circumstantial properties associated with the area; and generating, by the system based on the sentiment data, a response to a query for information associated with the area.

Abstract: Disclosed are a method for correcting a text, an electronic device and a storage medium. The method includes: acquiring a text to be corrected; acquiring a phonetic symbol sequence of the text to be corrected; and obtaining a corrected text by inputting the text to be corrected and the phonetic symbol sequence into a text correction model, in which, the text correction model obtains the corrected text by: detecting an error word in the text to be corrected, determining a phonetic symbol corresponding to the error word in the phonetic symbol sequence, and adding the phonetic feature corresponding to the phonetic symbol behind the error word to obtain a phonetic symbol text, and correcting the error word and the phonetic feature in the phonetic symbol text to obtain the corrected text.

Abstract: A method that includes extracting image features of a document image, executing an optical character recognition (OCR) engine on the document image to obtain OCR output, and extracting OCR features from the OCR output. The method further includes executing an anomaly detection model using features including the OCR features and the image features to generate anomaly score, and presenting anomaly score.

Abstract: A system and method that overcomes technological hurdles related to litigation-related management is disclosed. The technological hurdles were overcome with industry-transformative innovations in in-person, hybrid, and remote legal proceedings; court reporting; testimony management; trial preparation; and utilization of video evidence, to name several. These innovations resulted in many advantages, such as could-based testimony management, scalable digital transformation, dramatic savings in litigation costs, and fast turn-around on certified transcripts, to name several.

Abstract: The disclosed techniques automatically ingest new documents and store data extracted from the documents in a database for conversion into a different format. The disclosed techniques identify, via a backend API, newly released documents that include data for users and, based on the identifying, automatically ingest, via an ingestion call executed made by the backend API, the newly released documents. The disclosed techniques extract, using a computer vision model trained on different types of documents, a data from the newly released documents, where the extracting includes identifying locations within the documents from which to extract data. The disclosed techniques store the extracted data in the database storing data extracted from previously ingested documents for users in a text-based object format and convert, using a machine learning model trained on a plurality of metatags, data corresponding to a given user from the text-based object format to a queryable file format.

Abstract: Implementations are described herein for incorporating unstructured data into machine learning-based phenotyping. In various implementations, natural language textual snippet(s) may be obtained. Each natural language textual snippet may describe environmental or managerial features of an agricultural plot that exist during a crop cycle. A sequence-to-sequence machine learning model may be used to encode the natural language snippet(s) into embedding(s) in embedding space. The embedding(s) may semantically represent the environmental or managerial features of the agricultural plot. Using one or more phenotypic machine learning models, phenotypic prediction(s) may be generated about the agricultural plot based on the one or more semantic embeddings and additional structured data about the agricultural plot. Output may be provided at one or more computing devices that is based on one or more of the phenotypic predictions.

Abstract: In accordance with an embodiment, described herein is a system and method for use with a data analytics or other computing environment, for on-demand fetching of backend server logs into a frontend environment, such as for example a browser. Such on-demand log fetching can be specific to the working context that is for current session and current request; and can be accomplished by appending a parameter or flag to a current request. For each step associated with an instruction being performed, the method can create a timestamp within one or more log files associated with the instruction; and fetch the one or more log files associated with the instruction. Performance logs are then included with a dashboard response, and logged into the browser's console.

Abstract: A system and method for improving computer functionality by retrieving answers/responses to questions/input from a cache such as those used with chatbots and generative AI systems. Disclosed is a multi-layered caching strategy that focuses on the relevance of a cache hit by improving the quality of the answer. The approach demonstrates that response latency is significantly reduced when using caching and how a caching strategy could be applied in various layers of increasing relevance for a simple Question-and-Answer system with the possibility of extending to more complex generative AI interactions.

Abstract: Methods and systems are presented for auditing user feedback data corresponding to user communications received via at least one interface of a service provider. The user feedback data includes a first set of feedback categories associated with a first classification of the user communications. A first feature representation of the communications is generated from the user feedback data. The first feature representation includes a first set of textual data features extracted from the communications. A second feature representation is generated from the first feature representation using a first machine learning model. The second feature representation includes a second set of textual data features including semantic equivalents of the first set of features. A second machine learning model is trained with the second feature representation. A second classification of the user communications according to a second set of feedback categories is generated using the trained second machine learning model.

Abstract: A method and system for automating a process of downloading and analyzing messages from conversation rooms and chat rooms to determine topics, entities, context, and actionable items are provided. The method includes downloading a set of messages that have been communicated over a communication channel; analyzing each respective message in order to determine at least one respective topic that relates to each respective message; determining, based on a result of the analysis, metrics that relate to the set of messages; and storing historical data that relates to the downloaded set of messages and each of the metrics. The analysis may be performed by executing an artificial intelligence (AI) algorithm that is based on a Natural Language Processing (NLP) model and is trained by using the historical data.

Abstract: Embodiments provide for a temporal expression parser in a conversational data-to-text system are described herein. An example method may include receiving user query data comprising an input text string; generating, based at least in part on the input text string, a n-gram set comprising a plurality of n-gram elements; traversing each n-gram element in the n-gram set to generate a parse tree list comprising one or more parse trees based on a grammar template associated with the input text string; and generating, based at least in part on a last parse tree of the parse tree list, one or more semantic frames indicating a temporal expression associated with the input text string.

Abstract: A method for processing text data includes analyzing the text data to identify a plurality of keywords. The method also includes determining whether each of the plurality of keywords already exists in one or more databases. When a keyword in the plurality of keywords is not found in the one or more databases, the method includes tagging the keyword with a plurality of characters for storage. The plurality of characters includes at least a first character to indicate a start of the tagging, a second character to indicate a corresponding database for storing the keyword, and a third character to indicate an end of the tagging. The method also includes storing the tagged keyword in the corresponding database.

Abstract: There is included a method and apparatus comprising computer code configured to cause a processor or processors to perform generating one or more aligned inventories, wherein the one or more aligned inventories are generated using one or more word sense inventories, obtaining a word in a context sentence, determining one or more semantic equivalence scores indicating semantic similarity between the word in the context sentence and each of one or more associated glosses in the one or more aligned inventories using a semantic equivalence recognizer model, and predicting a correct sense of the word in the context sentence based on the determined one or more semantic equivalence scores.

Abstract: Systems and methods for creating predictor variables from unstructured data for prediction models are provided. A variable creation application receives unstructured data and processing the unstructured data to generate processed data. Based on the processed data, the variable creation application generates an attribute pool that contains multiple predictor variables generated by applying natural language processing (NLP) procedures on the processed data. The variable creation application further executes a prediction model on at least the predictor variables in the attribute pool to generate a prediction result. Based on the prediction result, the variable creation application evaluates the predictive power of each of the predictor variables and retains predictor variables that are predictive as input predictor variables for the prediction model.

Abstract: A response system includes an acquisition unit configured to acquire the question sentence of a user, a response sentence selection unit configured to select a response sentence, stored in a storage unit in advance, according to the acquired question sentence, a response sentence conversion unit configured to convert the selected response sentence according to the question sentence, and an output unit configured to output the converted response sentence. The response sentence conversion unit is configured to convert a word included in the selected response sentence to a word included in the question sentence based on the degree of similarity between the word included in the response sentence and the word included in the question sentence.

Abstract: Database systems and methods are provided for assigning structural metadata to records and creating automations using the structural metadata. One method of assigning structural metadata to a record associated with a conversation involves obtaining a plurality of utterances associated with the conversation, identifying, from among the plurality of utterances, a representative utterance for semantic content of the conversation, assigning the conversation to a group of semantically similar conversations based on the representative utterance, and automatically updating the record associated with the conversation at a database system to include metadata identifying the group of semantically similar conversations.

Abstract: Natural language generation technology is disclosed that applies artificial intelligence to structured data to determine content for expression in natural language narratives that describe the structured data. A graph data structure is employed, where the graph data structure comprises a plurality of nodes. Each of a plurality of the nodes (1) represents a corresponding intent so that a plurality of different nodes represent different corresponding intents and (2) is associated with one or more links to one or more of the nodes to define relationships among the intents.

Abstract: Data is received that includes a passage of text generated in response to a prompt which comprises a plurality of sentences. Thereafter, the passage of text is tokenized into a plurality of tokens each corresponding to a different word in the passage of text. A first classification head of an adaptive fine-tuned transforms classifies each of the tokens into one of a plurality of classes. A second classification head of the adaptive fine-tuned transformer model classifies each of the sentences as either including or not including an argument. Data can then be provided which characterizes the first and second classifications. Related apparatus, systems, techniques and articles are also described.

Abstract: A data processing system implements a method for training machine learning modes, including receiving a set of one or more unlabeled documents associated one or more first categories of documents to be used to train machine learning models to analyze the one or more unlabeled documents, and fine-tuning a first machine learning model and a second machine learning model based on the one or more unlabeled document to enable the first machine learning model to determine a semantic representation of the one or more first categories of document, and to enable the second machine learning model to classify the semantic representations according to the one or more first categories of documents, the first machine learning model and the second machine learning model having been trained using first unlabeled training data including a second plurality of categories of documents that do not include the one or more first categories of documents.

Abstract: This disclosure relates to extraction of tasks from documents based on a weakly supervised classification technique, wherein extraction of tasks is identification of mentions of tasks in a document. There are several prior arts addressing the problem of extraction of events, however due to crucial distinctions between events-tasks, task extraction stands as a separate problem. The disclosure explicitly defines specific characteristics of tasks, creates labelled data at a word-level based on a plurality of linguistic rules to train a word-level weakly supervised model for task extraction. The labelled data is created based on the plurality of linguistic rules for a non-negation aspect, a volitionality aspect, an expertise aspect and a plurality of generic aspects. Further the disclosure also includes a phrase expansion technique to capture the complete meaning expressed by the task instead of merely mentioning the task that may not capture the entire meaning of the sentence.

Abstract: A method to be executed on a computing device comprising (i) accessing and/or modifying a database to be automatically curated, (ii) optionally accessing additional data or information sources for further useful data or information, (iii) using one or more pre-trained large language models (LLMs) accessed via API or other connections, issuing prompts and retrieving prompt-answers and executing database curation requests that specify database curation tasks to be performed on at least one sub-structure of the database, the tasks comprising (a) a database enrichment task to compute new data records to be inserted into the database sub-structure, (b) a database verification task to verify, using the one or more LLMs, data contained in the sub-structure, and identify incorrect data, (c) a database update, and (d) a null-value or a missing value replacement task. The requested tasks are automatically performed via a computation comprising an adaptively generated prompt sequence.

Abstract: A system to identify cyber threat intelligence from a group of information is disclosed. The system includes a processing subsystem including a data sourcing module to fetch information. The processing subsystem includes a data processing module to extract textual information from the information. The processing subsystem includes a machine learning module including an entity analysis module to fragment the textual information to obtain entities. The entity analysis module is to analyze a label assigned to each of the entities to generate a first threat score. The machine learning module includes a semantic analysis module to summarize the entities to obtain a summarized text. The semantic analysis module is to evaluate sentiments pertaining to the summarized text. The semantic analysis module is configured to analyze the sentiments to generate a second threat score. The machine learning module includes a classifier module to classify the textual information categories.

Abstract: Provided is a method for querying questions. The method includes: acquiring input information of a user; acquiring intention information of the user based on the input information of the user; determining an answer generation rule; and generating, based on the input information and the intention information, a first answer in accordance with the answer generation rule, and providing the first answer to the user.

Abstract: Examples provide enhanced machine learning model accuracy through post-hoc confidence score calibration. A machine learning (ML) system receives results generated by an ML model, the results comprising at least one confidence score and electronic documents. The ML system processes the results generated by the ML model comprising performing document understanding by extracting data points from the electronic documents. The ML system associates the confidence score with the extracted data points and calibrates a confidence score associated with the extracted data points using a post-hoc calibration solution set. The ML system implements confidence scoring recalibration comprising aligning the confidence score with prediction accuracy and adjusting the generated confidence score by the recalibration. Based on adjusting the confidence score, the ML system extracts an individual element of information from the electronic documents comprising an extracted value.

Abstract: A system and method for generating task-specific text by processing multimodal inputs using machine-learning models is provided. The method may include accessing first sets of tokens associated with a desired task and one or more modalities associated with a context of the desired task. The method may further include determining a second set of tokens for each of the one or more modalities using a classifier network associated with the modality. The method may further include generating a number of embedding vectors by mapping the first sets of tokens and the second set of tokens associated with each of the one or more modalities to an embedding space. The method may further include producing a sequence of words addressing the desired task by processing the number of embedding vectors with an encoder-decoder network.

Abstract: A method for generating a dialogue state includes: acquiring a target dialogue state of a previous round of dialogue and dialogue information of a current round of dialogue; generating an initial dialogue state of the current round of dialogue according to the target dialogue state of the previous round of dialogue and the dialogue information of the current round of dialogue; and generating a target dialogue state of the current round of dialogue according to the initial dialogue state of the current round of dialogue and the dialogue information of the current round of dialogue.

Abstract: Described herein is a technique for mapping the raw text of a job title of an online job posting to an entity embedding, associated with an entity or entry of a title taxonomy. The raw text of the job title is first encoded to generate a multilingual word embedding in a multilingual word embedding space. Then, the vector representation of the job title, as represented in the multilingual word embedding space is translated, using a neural network, to a vector representation of the job title in the entity embedding space. Finally, a nearest neighbor search is performed to identify an entity embedding associated with an entity or entry in the title taxonomy that has a vector representation that is closest in distance to the vector output by the neural network.

Abstract: Methods and systems are described herein for efficiently labeling user utterances, which may encompass any communication received from a user within a conversational interaction, and identifying novel user intents for large amounts of data. A machine learning model may be used, which is trained on embeddings of utterance data, and which may employ methods like prototypical networks and hierarchical local binary classification for hierarchical multi-label multi-class classification.

Abstract: Techniques are disclosed for generating anomaly scores for a neuro-linguistic model of input data obtained from one or more sources. According to one embodiment, generating anomaly scores includes receiving a stream of symbols generated from an ordered stream of normalized vectors generated from input data received from one or more sensor devices during a first time period. Upon receiving the stream of symbols, generating a set of words based on an occurrence of groups of symbols from the stream of symbols, determining a number of previous occurrences of a first word of the set of words, determining a number of previous occurrences of words of a same length as the first word, and determining a first anomaly score based on the number of previous occurrences of the first word and the number of previous occurrences of words of the same length as the first word.

Abstract: A method, computer program, and computer system for training a graph-to-text generation network is provided. Encoded graph information corresponding to a target sentence is received, and the encoded graph information is decoded based on a biaffine attention score. One or more loss values are determined based on the decoded information, whereby the text-to-graph generation network is trained by minimizing the one or more loss values. A first loss value is generated by reconstructing one or more triple relations based on the biaffine attention score, and a second loss value predicts the graph as a linearized sequence.

Abstract: There are provided systems and methods for named entity recognition in chat dialogues for customer relationship management systems. A service provider, such as an electronic transaction processor for digital transactions, may provide live chat service channels for assistance through live agents and chatbot services. When interacting with these channels, a user may engage in a chat dialogue with live agents. This may include lines of texts corresponding to the exchanged messages and may include named entities for particular types or categories of words that refer to a particular object or thing. To identify these named entities, a natural language processor may utilize machine learning and other engines for named entity recognition in customer relationship management systems to highlight the named entities in live service chats. Agents of the systems may view content that identify the named entities and interact with the named entities to view descriptions.