Abstract: A natural language programming system may configure a machine learning (ML) model to translate natural language descriptions into constrained language statements. The constrained language statements may express the natural language descriptions using a constrained subset of natural language. The constrained subset of natural language includes words with unambiguous semantics and with meaning that has a clear and singular interpretation. The constrained language statements with unambiguous semantics enable construction of valid statements in high-level “English-like” executable programming language. With the present system, a user does not need to learn a new programming language but rather learn to constrain their natural language statements to a subset of the natural language (“constrained language”) and to generate executable programs.

Abstract: A reading comprehension system may include an authoring tool to help generate adaptable dialogs and a reading tool to conduct adaptable dialog sessions with students. The authoring tool may receive and process stories to generate labeled stories and information models. The information models may provide the conceptual structures that an effective reader should build while reading and understanding a story. The system may use dialog models for general dialogs and information models for story specific dialogs to guide adaptable dialog sessions with students. During the adaptable dialog sessions, the system may constantly assess and guide the student's progress in the understanding the current story and in general reading comprehension development. Using the labeled stories and dialog sessions as training data, the system may learn how to dialog effectively with the students, to gather an evolving understanding of the student's abilities, and to acquire knowledge about the world or the story.

Abstract: A natural language programming system may configure a machine learning (ML) model to translate natural language descriptions into constrained language statements. The constrained language statements may express the natural language descriptions using a constrained subset of natural language. The constrained subset of natural language includes words with unambiguous semantics and with meaning that has a clear and singular interpretation. The constrained language statements with unambiguous semantics enable construction of valid statements in high-level “English-like” executable programming language. With the present system, a user does not need to learn a new programming language but rather learn to constrain their natural language statements to a subset of the natural language (“constrained language”) and to generate executable programs.

Abstract: This disclosure covers methods, systems, and computer-readable media that select answer choices from potential answer choices for a digital question based on responses to other digital questions and/or embedded user data. In certain embodiments, the disclosed systems select answer choices from potential answer choices for a digital question based on a multiple choice response. Furthermore, in some embodiments, the disclosed systems select answer choices from potential answer choices for a digital question based on keywords and/or sentiment values identified by analyzing a text response. In some embodiments, the disclosed systems select answer choices for a digital question from a dynamic choice reference dataset that comprises potential answer choices. Additionally, in one or more embodiments, the disclosed systems train and/or utilize a machine-learning model to select answer choices from potential answer choices for a digital question based on a response.

Abstract: The present disclosure relates to a response prediction system that intelligently optimizes the quality of responses to a survey by predicting response quality and generating suggested changes (e.g., improving question ordering, question phrasing, question type, etc.). For example, in one or more embodiments, the response prediction system predicts response quality based on extracted survey characteristics. The response prediction system uses the predicted response quality to generate suggested changes before publishing the survey. Additionally, the response prediction system collects feedback by analyzing responses after the survey has been published to update suggested changes specific to the survey.

Abstract: This disclosure covers methods, systems, and computer-readable media that select answer choices from potential answer choices for a digital question based on responses to other digital questions and/or embedded user data. In certain embodiments, the disclosed systems select answer choices from potential answer choices for a digital question based on a multiple choice response. Furthermore, in some embodiments, the disclosed systems select answer choices from potential answer choices for a digital question based on keywords and/or sentiment values identified by analyzing a text response. In some embodiments, the disclosed systems select answer choices for a digital question from a dynamic choice reference dataset that comprises potential answer choices. Additionally, in one or more embodiments, the disclosed systems train and/or utilize a machine-learning model to select answer choices from potential answer choices for a digital question based on a response.

Abstract: An apparatus for controlling the temperature of a supply of water by selective injection of steam is disclosed. The apparatus comprises a water supply conduit which includes a water inlet end and a water outlet end. Steam is supplied to the apparatus by a steam supply conduit which supplies steam to the water supply conduit at a predetermined location between the water inlet end and the water outlet end of the water supply conduit. The steam entering the water supply conduit is controlled by a steam supply control valve located on the steam supply conduit. A pressure differential sensing means senses the difference in pressure along the water supply conduit between a first point in said water supply conduit, upstream of said predetermined location and a second point in the water supply conduit downstream of the predetermined location. A means for controlling the control valve means in response to this sensed pressure differential is also required.