Abstract: A computing system identifies an incoming voice call from a user device to an agent device associated with the computing system. The computing system generates a transcription of the incoming voice call using one or more natural language processing techniques. The computing system extracts a problem description from the transcription. The problem description indicates a topic for the incoming voice call. A first machine learning model estimates a situation vector from the problem description. A second machine learning model identifies a pre-existing situation vector that closely matches the estimated situation vector. The computing system retrieves a situation description that corresponds to the identified pre-existing situation vector.

Abstract: A method including training, using training data including a first ontological hierarchical level, trained machine learning models (MLMs) to predict a first output type including a second ontological hierarchical level different than the first ontological hierarchical level. The method also includes generating instances of the first output type by executing the trained MLMs on unknown data including the first ontological hierarchical level. Outputs of the trained MLMs include the instances at the second ontological hierarchical level. The method also includes training, using the instances, a voting classifier MLM to predict a selected instance from the instances. The voting classifier MLM is trained to predict the selected instance to satisfy a criterion including a third ontological hierarchical level different than the first ontological hierarchal level and the second ontological hierarchical level.

Abstract: A method including inputting, into a phrase recognition model comprising a neural network, a vector comprising a plurality of ngrams of text. The method also includes applying, using the phrase recognition model, a filter to the plurality of ngrams during execution. The filter has a skip word setting of at least one. The method also includes determining, based on the skip word setting, at least one ngram in the vector to be skipped to form at least one skip word. The method also includes outputting an intermediate score for a set of ngrams that match the filter. The method also includes calculating a scalar number representing a semantic meaning of the at least one skip word. The method also includes generating based on the scalar number and the intermediate score, a final score for the set of ngrams. A computer action is performed using the final score.

Abstract: Automatic keyphrase labeling and machine learning training may include a processor extracting a plurality of keywords from at least one search query that resulted in a selection of a document appearing in a search result. For each of the plurality of keywords, the processor may determine a probability that the keyword describes the document. The processor may generate one or more keyphrases by performing processing including selecting each of the plurality of keywords having a probability greater than a predetermined threshold value for insertion into at least one of the one or more keyphrases and assembling the one or more keyphrases from the selected plurality of keywords. The processor may label the document with the keyphrase.

Abstract: A computing system identifies an incoming voice call from a user device to an agent device associated with the computing system. The computing system generates a transcription of the incoming voice call using one or more natural language processing techniques. The computing system extracts a problem description from the transcription. The problem description indicates a topic for the incoming voice call. A first machine learning model estimates a situation vector from the problem description. A second machine learning model identifies a pre-existing situation vector that closely matches the estimated situation vector. The computing system retrieves a situation description that corresponds to the identified pre-existing situation vector.

Abstract: In one aspect, the present disclosure relates to a method of generating business descriptions performed by a server, said method may include: receiving a plurality of invoices, each invoice being associated with a business of a plurality of businesses; extracting a plurality of texts from the plurality of invoices; embedding the plurality of texts to a vector space to obtain a plurality of invoice vectors; generating a plurality of clusters in the vector space, each cluster of the plurality of clusters comprising at least one invoice vector of the plurality of invoice vectors; generating a description for a cluster, the description for the cluster representing all invoice vectors assigned to the cluster; for each business of the plurality of businesses that has at least one invoice vector assigned to the cluster, associating the business with the description; and indexing the plurality of businesses within a database by the generated descriptions.

Abstract: A method involves receiving search queries, having search terms, submitted to at least one computerized search engine. For each query, a corresponding pairwise relation in the search queries is calculated. The corresponding pairwise relation is a corresponding probability of a potential edge relationship between at least two terms. Thus, potential edges are formed. A general graph of the terms is constructed by selecting edges from the potential edges. The general graph is nodes representing the terms used in the search queries. The general graph also is edges representing semantic relationships among the nodes. A hierarchical graph is constructed from the general graph by altering at least one of the edges among the nodes in the general graph to form the hierarchical graph.

Abstract: A computing system identifies an incoming voice call from a user device to an agent device associated with the computing system. The computing system generates a transcription of the incoming voice call using one or more natural language processing techniques. The computing system extracts a problem description from the transcription. The problem description indicates a topic for the incoming voice call. A first machine learning model estimates a situation vector from the problem description. A second machine learning model identifies a pre-existing situation vector that closely matches the estimated situation vector. The computing system retrieves a situation description that corresponds to the identified pre-existing situation vector.

Abstract: A method including embedding, by a trained issue MLM (machine learning model), a new natural language issue statement into an issue vector. An inner product of the issue vector with an actions matrix is calculated. The actions matrix includes centroid-vectors calculated using a clustering method from a second output of a trained action MLM which embedded prior actions expressed in natural language action statements taken as a result of prior natural issue statements. Calculating the inner product results in probabilities associated with the prior actions. Each of the probabilities represents a corresponding estimate that a corresponding prior action is relevant to the issue vector. A list of proposed actions relevant to the issue vector is generated by comparing the probabilities to a threshold value and selecting a subset of the prior actions with corresponding probabilities above the threshold. The list of proposed actions is transmitted to a user device.

Abstract: A processor may generate a cluster of at least two (or any other minimal cluster size) of a plurality of vectors using a density-based clustering algorithm. The generating may include optimizing at least one hyperparameter of the density-based clustering algorithm by minimizing a loss function to increase a cluster count and decrease a cluster variance. The processor may select a vector closest to the center of the cluster as a representative vector.

Abstract: A processor may receive a request to display a user interface (UI) for a user account. The processor may determine a context for the UI from information specific to the user account. The processor may select one of a plurality of UI elements based on the determining. In some embodiments, the selecting may include evaluating a value function taking the information specific to the user account and information about the context as inputs. The processor may cause the UI including the selected one of the plurality of UI elements to be displayed in response to the request.

Abstract: A method including transcribing, into digital tokens, utterances from a conversation between an agent and a person. The method also includes embedding the digital tokens into an utterances tensor including sequences of the digital tokens. The method also includes obtaining a metadata tensor by encoding metadata related to the utterances into the metadata tensor. The method also includes executing a machine learning model which takes, as input, the utterances tensor and the metadata tensor, and which outputs a predicted source article predicted to be related to the utterances. The method also includes generating an interactive link to the predicted source article.

Abstract: A computing system identifies an incoming voice call from a user device to an agent device associated with the computing system. The computing system generates a transcription of the incoming voice call using one or more natural language processing techniques. The computing system extracts a problem description from the transcription. The problem description indicates a topic for the incoming voice call. A first machine learning model estimates a situation vector from the problem description. A second machine learning model identifies a pre-existing situation vector that closely matches the estimated situation vector. The computing system retrieves a situation description that corresponds to the identified pre-existing situation vector.

Abstract: Embodiments disclosed herein may extract trending topics from phone call transcripts or any type of text data. The phone call transcripts may be collected for a time period and the time period may be divided into time spans. For each time span having more than a threshold number of phone call transcripts, n-grams from the phone call transcripts may be extracted. The extracted n-grams may be contextually clustered by converting the n-grams into their embedding vectors, reducing the dimensionality of the embedding vectors, and clustering similar reduced dimensionality embedding vectors. Normalized occurrences of one or more clusters may be generated. The recent mean of the number of occurrences of the normalized clusters may be compared with the historical mean and offset by historical standard deviation to generate a modified Z-score. N-grams corresponding to the clusters with high Z-scores may be identified as trending topics.

Abstract: Systems and methods to select a product title are described. The system identifies a set of item listings respectively describing items being offered for sale on a network-based marketplace. Each item listing includes a product identifier that matches and is not associated with a product title on the network-based marketplace. Each item listing also includes an item title. The system extracts feature values from the item listings and processes the feature values. The system evaluates the feature values to adopt a product title from an item title included in the set of item titles. The system generates a product user interface including the product title. Finally, the system communicates the product user interface, over a network, for display on a client machine. The product user interface includes the product title.

Abstract: A method of score prediction uses hierarchical attention. Word features, positioning features, participant embedding features, and metadata are extracted from a transcript of a conversation. A word encoder vector is formed by multiplying weights of a word encoder layer to one or more word features. A sentence vector is formed by multiplying weights of a word attention layer to word encoder vectors. An utterance encoder vector is formed by multiplying weights of an utterance encoder layer to the sentence vector. A conversation vector is formed by multiplying weights of an utterance attention layer to utterance encoder vectors. The utterance encoder vector is combined with one or more positioning features and one or more participant embedding features. A predicted net promoter score is generated by multiplying weights of an output layer to the conversation vector combined with the metadata. The predicted net promoter score is presented in a list of conversations.

Abstract: A method may including obtaining a voice transcript corpus and a chat transcript corpus, extracting voice transcript sentences from the voice transcript corpus and chat transcript sentences from the chat transcript corpus, encoding, by a series of neural network layers, the voice transcript sentences to generate voice sentence vectors, encoding, by the series of neural network layers, the chat transcript sentences to generate chat sentence vectors, determining, for each voice sentence vector, a matching chat sentence vector to obtain matching voice-chat vector pairs, and adding, to a parallel corpus, matching voice-chat sentence pairs using the matching voice-chat vector pairs. Each of the matching voice-chat sentence pairs may include a voice transcript sentence and a matching chat transcript sentence. The method may further include training a disfluency remover model using the parallel corpus.

Abstract: Methods and systems classify and cluster invoice data. An invoice is obtained. A category vector is generated from an invoice string of the invoice with a dense layer of a machine learning model that includes an embedding layer, a neural network layer, and the dense layer. A suggestion is selected with a selection engine and in response to comparing the category vector to a set of clusters. The suggestion is presented.

Abstract: A method for recommending offerings to a business may include: receiving a request for recommended business offerings from a device; receiving business data associated with a business from the device, the business data comprising invoice data associated with the business; embedding the business data to a vector space to obtain a business vector, the vector space comprising a plurality of other vectors associated with other businesses; calculating a relation metric between the business vector and a vector of the plurality of other vectors, the vector being associated with a second business, the relation metric representing a degree of relation between the business and the second business; determining that the relation metric is above a pre-defined threshold value; and responsive to the determining, sending business data associated with the second business to the device, the business data associated with the second business comprising invoice data associated with the second business.

Abstract: Aspects of the present disclosure provide techniques for detecting sensitive information. Embodiments include determining a first likelihood that a record contains at least a given type of sensitive information using a first detection technique that involves providing one or more inputs to a machine learning model based on the record and receiving the first likelihood as an output from the machine learning model based on the one or more inputs. Embodiments include determining a second likelihood that the record contains at least the given type of sensitive information using a second detection technique comprising a search of the record. Embodiments include applying a policy to determine whether the record contains sensitive information based on the first likelihood and the second likelihood. Embodiments include performing one or more actions based on whether the record contains sensitive information.