Abstract: A method for executing a computerized query includes receiving a new query from a user device. The query includes natural language text. Based on a type of user, and using an alternative term generator, a selected data model is selected from among pre-determined data models. The selected data model is particular to the type of user. Each of the pre-determined data models includes a corresponding semantic graph data model that establishes semantic relationships between words. Query words in the natural language text are compared to the selected data model using the alternative term generator to find at least one alternative term. The alternative term has a semantic relationship to a query word in query words. The semantic relationship exceeds a first threshold value. The alternative term is substituted for a query word to form a revised query. The revised query is executed on a search engine using the alternative terms.

Abstract: A method for text classification involves generating, using a bilingual embedding model, source language embeddings for source language documents; obtaining source language document labels of the source language documents; and training a source language classifier model and a label embedding network, executing on a computing system, using the source language embeddings and the source language document labels. The method further involves generating pseudo-labels for unlabeled target language documents, by: generating, using the bilingual embedding model, target language embeddings for the unlabeled target language documents, and applying the source language classifier model and the label embedding network to the target language embeddings to obtain the pseudo-labels for the unlabeled target language documents. In addition, the method involves training a target language classifier model executing on the computing system using the target language embeddings and the pseudo labels.

Abstract: The invention relates to a method. The method includes receiving a flawed input comprising a domain specific misspelling. The method further includes encoding, by an encoder machine learning model executing on a computer processor, the flawed input on a per character basis to create a context vector. The method further includes decoding, by a decoder machine learning model executing on the computer processor, the context vector on the per character basis to create a rephrased input lacking the domain specific misspelling. The method further includes presenting the rephrased input.

Abstract: A method for decoding a natural language user query involves obtaining the user query submitted by a user, segmenting the user query into words, generating a character embedding for each of the words, and generating a word embedding for each of the words. The method further involves obtaining a clickstream from tracked clicks of the user, generating a clickstream embedding from the clickstream, and for each of the words, generating a unified feature representation based on the character embedding and the word embedding for each of the words, and the clickstream embedding. The method also involves decoding the unified feature representations to obtain a decoded user query, and processing the user query using the decoded user query.

Abstract: A method for decoding a natural language user query involves obtaining the user query submitted by a user, segmenting the user query into words, generating a character embedding for each of the words, and generating a word embedding for each of the words. The method further involves obtaining a clickstream from tracked clicks of the user, generating a clickstream embedding from the clickstream, and for each of the words, generating a unified feature representation based on the character embedding and the word embedding for each of the words, and the clickstream embedding. The method also involves decoding the unified feature representations to obtain a decoded user query, and processing the user query using the decoded user query.