Abstract: In one embodiment, a computer-implemented method executed using an application server computer that is communicatively coupled to a database via a telecommunication network, the database comprising a digitally stored relational table schema storing a plurality of term sets, each of the term sets comprising a plurality of terms, the application server computer hosting an application program programmed with a fill-in-the-blank (FITB) question generator service, the method comprising: using the application server computer, receiving input specifying a particular term that does not include an FITB portion, and in response thereto, using the application server computer, executing an inference stage of a trained machine learning model over the particular term as input to generate output predictions comprising a token position and number of tokens of a target span of an FITB portion; using the application server computer, post-processing the output predictions by computing a penalty score, selecting a final position

Abstract: The computer-implemented method includes obtaining a data input and determining its eligibility using an eligibility model. This eligibility is assessed by identifying the language and subject of the data and confirming whether they fall within a predefined set of acceptable languages and subjects. If eligible, the input is classified as a practice-test-type using a data classification model. Subsequently, a text classification model identifies and classifies a first selection from the practice-test-type input as a candidate question. The candidate question is represented using a first word embedding, while a generative model produces a suggested question based on the candidate question, represented using a second word embedding. A similarity score between these embeddings is calculated, and if it exceeds a selected threshold, the suggested question is selected as the practice test question. Based on the suggested question, the generative model produces a suggested answer.

Abstract: The computer-implemented method includes obtaining strike distance keywords for a target website, which, when optimized for these keywords, experiences an increase in web traffic. Also, the method includes obtaining parameter sets associated with the strike distance keywords. For each strike distance keyword, a semantic embedding vector is generated, utilizing keyword-related information. Subsequently, an appended semantic embedding vector is formed by incorporating parameters from obtained parameter sets, such as keyword difficulty or search volume into the original vector. This appended semantic embedding vector is then input into a trained machine-learning model tailored to forecast traffic increases for the target website when it is optimized for the respective strike distance keyword. The model assesses traffic increase indicators for each strike distance keyword.

Abstract: In one embodiment, a computer-implemented method comprises, using an application server computer that is communicatively coupled to a database via a telecommunication network, the database comprising a digitally stored relational table schema storing a plurality of term sets, each of the term sets comprising a plurality of terms, the application server computer hosting an application program programmed with a plurality of distractor selection algorithms; executing each of the distractor algorithms to access a particular term from among the plurality of the terms as an input and to generate a plurality of corresponding first interim sets of candidate distractor terms, for the particular term, as an output; executing a first inference stage of a within-set machine learning model over the same particular term as input to generate classification output comprising a second interim set of candidate distractor terms, for the particular term; executing a second inference stage of a cross-algorithm ranking machine lea

Abstract: In one embodiment, a computer-implemented method can use a server computer to obtain from a client computer a text input in a query from a user and access in digital data storage coupled to the server computer a plurality of digital images. The computer-implemented method can train a deep learning model to determine a first embedding for the text input and a second embedding of each of the plurality of images. The computer-implemented method can identify one or more relevant images based on a respective similarity of the first embedding to the second embedding. The computer-implemented method can determine image informativeness and confidence scores for information terms of each of the one or more relevant images. The computer-implemented method can transmit to the client computer in response to obtaining the text input, instructions for presenting a user interface comprising the one or more relevant images and the confidence scores.

Abstract: An example method embodying the disclosed technology comprises: digitally storing Teacher models and a Student model at a server computer; training each model with a corpus of unlabeled training data using Masked Language Modeling; fine-tuning each Teacher model for an ASAG task with labeled ground truth data; executing each Teacher model to generate and digitally store a respective set of class probabilities on an unlabeled task-specific data set for the ASAG task; further training the Student model by a linear ensemble of the Teacher models using KD; receiving, at the server computer, digital input comprising a target response text and a corresponding target reference answer text; programmatically inputting the target response text and the corresponding target reference answer text to the Student model, thereby outputting a corresponding predicted binary label; displaying correction data indicating the corresponding predicted binary label in a GUI; and, optionally, displaying explainability data in the GUI.

Abstract: An example method embodying the disclosed technology comprises: digitally storing Teacher models and a Student model at a server computer; training each model with a corpus of unlabeled training data using Masked Language Modeling; fine-tuning each Teacher model for an ASAG task with labeled ground truth data; executing each Teacher model to generate and digitally store a respective set of class probabilities on an unlabeled task-specific data set for the ASAG task; further training the Student model by a linear ensemble of the Teacher models using KD; receiving, at the server computer, digital input comprising a target response text and a corresponding target reference answer text; programmatically inputting the target response text and the corresponding target reference answer text to the Student model, thereby outputting a corresponding predicted binary label; displaying correction data indicating the corresponding predicted binary label in a GUI; and, optionally, displaying explainability data in the GUI.