Abstract: A computerized system and method may provide automated clustering procedures where each clustered entity or node may be included in a plurality of clusters (e.g., more than a single cluster). Clustering procedures provided by some embodiments of the invention may involve measuring and/or quantifying degrees of relevance and/or generality for a plurality of entities or nodes. In some embodiments, a clustering procedure may be used, e.g., to generate a hierarchical, multi-tiered taxonomy of such entities. A computerized system comprising a processor, and a memory, may be used for ranking a plurality of nodes; select nodes based on the ranking; cluster selected nodes into intermediate clusters; calculate distances between unselected nodes and intermediate clusters; and cluster unselected nodes and intermediate clusters into final clusters based on the calculated distances.

Abstract: A computerized system and method may provide automated clustering procedures where each clustered entity or node may be included in a plurality of clusters (e.g., more than a single cluster). Clustering procedures provided by some embodiments of the invention may involve measuring and/or quantifying degrees of relevance and/or generality for a plurality of entities or nodes. In some embodiments, a clustering procedure may be used, e.g., to generate a hierarchical, multi-tiered taxonomy of such entities. A computerized system comprising a processor, and a memory, may be used for ranking a plurality of nodes; select nodes based on the ranking; cluster selected nodes into intermediate clusters; calculate distances between unselected nodes and intermediate clusters; and cluster unselected nodes and intermediate clusters into final clusters based on the calculated distances.

Abstract: A computerized system and method may provide a robust, automated clustering procedure, including handling of outlier points, which may involve measuring and/or quantifying degrees of relevance and/or generality for a plurality of input entities. In some embodiments, a clustering procedure may be used, e.g., to generate a hierarchical, multi-tiered taxonomy of such entities. In some embodiments, a computerized system comprising a processor, and a memory, may be used for calculating a distance between nodes for each of a plurality of pairs of nodes, where the pairs may comprise a plurality of input entities and/or initial clusters; selecting one or more of the pairs based on the calculated distances; and merging one or more of the selected pairs, which may include a common node, into one or more final clusters. Some embodiments of the invention may allow routing interactions between remotely connected computer systems based on an automatically generated taxonomy.

Abstract: A computerized system and method may automatically generate a hierarchical, multi-tiered taxonomy based on measuring and/or quantifying degrees of generality for a plurality of input entities. In some embodiments of the invention, a computerized system comprising a processor, and a memory including a plurality of entities such as documents or text files, may be used for extracting words from a plurality of documents; calculating generality scores for the extracted words; selecting some of the extracted words as exemplars based on the scores; and clustering unselected words under appropriate exemplars to produce or output a corresponding taxonomy. Some embodiments of the invention may allow categorizing interactions among remotely connected computers using a domain taxonomy, and routing interactions between remotely connected computer systems based on the taxonomy.

Abstract: A system and method for determining an embedding for a document (e.g. representing the document in vector space) by determining for the document a preliminary document embedding; determining for the document a document topic embedding based on a set of nearest topics to the preliminary document embedding; determining for each phrase in the document a topic relevancy score based on the document topic embedding and the embedding associated with the phrase; using a ranking algorithm to determine a saliency score for each phrase in the document, each saliency score based on the topic relevancy score for the phrase, and an inverse frequency score for the phrase; and calculating an embedding for the document using the saliency scores and embedding, for the phrases in the document.

Abstract: A system and method for training and using a text embedding model may include creating structured phrases from an input text; creating turn input samples from the input text, each turn input sample based on only or consisting of input from a single turn within the text and being formed by removing structure from structured phrases; and training an embedding model using the structured phrases and turn input samples. Call input samples may be created based on input from more than one turn within the text. At each level of resolution (e.g. phrase, speaker, call), a different level of resolution may be used to create input samples. At inference an embedding may be based on a weighted combination of the sub-terms within an input phrase, each weight being based on an inverse document frequency measure for the sub-term associated with the weight.

Abstract: A system and method for determining an embedding for a document (e.g. representing the document in vector space) by determining for the document a preliminary document embedding; determining for the document a document topic embedding based on a set of nearest topics to the preliminary document embedding; determining for each phrase in the document a topic relevancy score based on the document topic embedding and the embedding associated with the phrase; using a ranking algorithm to determine a saliency score for each phrase in the document, each saliency score based on the topic relevancy score for the phrase, and an inverse frequency score for the phrase; and calculating an embedding for the document using the saliency scores and embedding, for the phrases in the document.

Abstract: A system and method for training and using a text embedding model may include creating structured phrases from an input text; creating turn input samples from the input text, each turn input sample based on only or consisting of input from a single turn within the text and being formed by removing structure from structured phrases; and training an embedding model using the structured phrases and turn input samples. Call input samples may be created based on input from more than one turn within the text. At each level of resolution (e.g. phrase, speaker, call), a different level of resolution may be used to create input samples. At inference an embedding may be based on a weighted combination of the sub-terms within an input phrase, each weight being based on an inverse document frequency measure for the sub-term associated with the weight.