Abstract: Techniques described herein involve providing a dynamic content classification and contextualization system using machine learning models. Embodiments include determining, using a machine learning model, a classification of content contained in an input provided to the machine learning model. Embodiments further include generating, using the machine learning model, a confidence score for the classification. Embodiments further include extracting one or more entities from the content based on determining that the confidence score is below a threshold score. Embodiments further include retrieving, using a language processing machine learning model, contextual data from a searchable knowledge base based on the one or more entities extracted from the content. Embodiments further include generating, using the machine learning model, an updated classification based on the retrieving. Embodiments further include performing an action based on the updated classification.

Abstract: A method including applying a language model to datasets to generate topics assigned to the datasets. Each of the topics includes at least one of a natural language text word and a natural language phrase. The method also includes applying an encoding model to the topics to generate a corresponding vector data structures storing embedded topics. Each embedded topic of the embedded topics is associated with one corresponding vector in the vector data structures. The method also includes applying a clustering model to the vector data structures to generate a cluster including a subset of the vector data structures. The subset includes a reduced number of the vector data structures. The method also includes modifying, according to the cluster, the datasets.

Abstract: Certain aspects of the disclosure provide a method for automatically identifying related communications, comprising: tokenizing a new communication from a first sender into a first plurality of tokens; identifying a plurality of communications associated with the first sender; for each respective communication: generating a self-attention data element comprising a plurality of attention values determined based on the first plurality of tokens associated with the new communication and a second plurality of tokens associated with the respective communication; determining a first plurality of features from the self-attention data element; and processing, with a machine learning (ML) model trained to identify related communications, the first plurality of features and to generate a score indicating a relatedness of the respective communication to the new communication; and determining communication(s) of the plurality of communications are related to the new communication based on each of the communication(s) hav

Abstract: A Large Language Model (LLM) for classifying documents by identifying indicators within the documents. A smart caching mechanism stores document classifications and associated indicators output from the LLM. The database contains document details, classifications, and associated indicators. A classification module classifies a new document by analyzing it for indicators, checking the cache for a match, and querying the database for the indicators if no match is found. The module applies a majority vote based on the classifications associated with the indicators.

Abstract: Natural language-based question answering systems and techniques are generally described. In some examples, a natural language processing system, first natural language data. The natural language processing system may determine first slot data included in the first natural language data. A set of content items associated with the first slot data may be determined. A first machine learning model may use the first natural language data to generate prediction data associated with a first attribute among a list of attributes of the set of content items. In some examples, a first value associated with the first attribute for a first content item of the set of content items may be determined. Second natural language data may be generated based at least in part on the first value. The second natural language data may include a response to the first natural language data.