Abstract: Certain aspects of the disclosure provide techniques for categorization by a device. An example method includes receiving input information regarding a plurality of classification targets and a plurality of categories for classification of the plurality of classification targets; generating a plurality of embeddings for the input information using a first model, the plurality of embeddings including: a set of first embeddings associated with the plurality of classification targets, and a set of second embeddings associated with the plurality of categories; determining that a similarity score for the set of first embeddings and the set of second embeddings fails to satisfy a threshold; generating, based on the similarity score failing to satisfy the threshold and using a graph neural network (GNN), a classification of the plurality of classification targets in accordance with the plurality of categories; and outputting information regarding the classification.

Abstract: A method is disclosed. The method includes: obtaining a help request associated with a user operating an application and a click stream of the user within the application; generating a feature data structure based on the help request and the click stream; generating, by applying the feature data structure to a machine learning model, a topic data structure including a plurality of scores corresponding to a plurality of topics; obtaining a plurality of topic distributions corresponding to a plurality of articles; identifying, by applying the topic data structure to the plurality of topic distributions, a subset of the plurality of articles for the user; and displaying, in response to the help request, a graphical user interface (GUI) including a plurality of links to the subset of the plurality of articles.

Abstract: One or more embodiments are directed to identifying documents with topic vectors by training a machine learning model with a training documents generated from text collections, receiving, after generating a list of topic vectors for the plurality of text collections, an additional text collection, and generating an additional topic vector for the additional text collection without training the machine learning model on the additional text collection. One or more embodiments further include updating the list of topic vectors with additional topic vectors that includes the additional topic vector, receiving a first topic vector based on a first text collection generated in response to user interaction, and matching the first topic vector to the additional topic vector. One or more embodiments further include presenting a link corresponding to the additional text collection in response to matching the first topic vector to the additional topic vector.