Abstract: System and method for displaying a user interface of an evaluation system configured to evaluate predicted answers generated by a machine learning system. For example, the method includes receiving textual data and a predicted answer to a question associated with a text object. The text object includes a structured data field of the textual data. The predicted answer includes a confidence level. The confidence level is determined by a machine learning system. In response to determining the confidence level being larger than or equal to a predetermined confidence threshold, the predicted answer and a reference is stored in a storage for retrieval and display. The reference indicates a location of the text object in the textual data. In response to determining the confidence level being smaller than the predetermined confidence threshold, the question and the text object associated with the question is displayed.

Abstract: In one embodiment, a method for adaptive training of a machine learning system configured to predict answers to questions associated with textual data includes receiving predicted answers to questions associated with textual data. The predicted answers are generated based at least in part on one or more first models of a machine learning system. The one or more first models are associated with a first accuracy score. The method further includes determining based at least in part on a quality control parameter whether an evaluation of the questions by one or more external entities is required. In response to determining based at least in part on the quality control parameter that an evaluation of the questions by one or more external entities is required, the questions associated with the textual data and the textual data are sent to the one or more external entities for evaluation.

Abstract: System and method for displaying a user interface of an evaluation system configured to evaluate predicted answers generated by a machine learning system. For example, the method includes receiving textual data and a predicted answer to a question associated with a text object. The text object includes a structured data field of the textual data. The predicted answer includes a confidence level. The confidence level is determined by a machine learning system. In response to determining the confidence level being larger than or equal to a predetermined confidence threshold, the predicted answer and a reference is stored in a storage for retrieval and display. The reference indicates a location of the text object in the textual data. In response to determining the confidence level being smaller than the predetermined confidence threshold, the question and the text object associated with the question is displayed.

Abstract: In one embodiment, a method for adaptive training of a machine learning system configured to predict answers to questions associated with textual data includes receiving predicted answers to questions associated with textual data. The predicted answers are generated based at least in part on one or more first models of a machine learning system. The one or more first models are associated with a first accuracy score. The method further includes determining based at least in part on a quality control parameter whether an evaluation of the questions by one or more external entities is required. In response to determining based at least in part on the quality control parameter that an evaluation of the questions by one or more external entities is required, the questions associated with the textual data and the textual data are sent to the one or more external entities for evaluation.

Abstract: Systems and methods include receiving textual data and a predicted answer to a question associated with a text object. The text object includes a structured data field of the textual data. The predicted answer includes a confidence level. The confidence level is determined by a machine learning system based at least in part on one or more models of the machine learning system and the textual data. In response to determining the confidence level being larger than or equal to a predetermined confidence threshold, the predicted answer and a reference is stored in a storage for retrieval and display. The reference indicates a location of the text object in the textual data. In response to determining the confidence level being smaller than the predetermined confidence threshold, the question and the text object associated with the question is displayed, at the user interface, to a user for inputting a true answer.

Abstract: System and method for adaptive training of a machine learning system processing textual data. For example, a method for adaptive training of a machine learning system configured to predict answers to questions associated with textual data includes receiving predicted answers to questions associated with textual data. The predicted answers are generated based at least in part on one or more first models of a machine learning system. The one or more first models are associated with a first accuracy score. The method further includes determining based at least in part on a quality control parameter whether an evaluation of the questions by one or more external entities is required. In response to determining based at least in part on the quality control parameter that an evaluation of the questions by one or more external entities is required, the questions associated with the textual data and the textual data are sent to the one or more external entities for evaluation.

Abstract: A system finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: Systems and methods for generating logical documents for a document evaluation system are provided. For example, a method for generating logical documents for a document evaluation system includes receiving a first child document associated with a master document. The master document includes one or more master terms. The first child document includes one or more first child terms and a first date. The method further includes generating a logical document based at least in part on the master document. The logical document includes one or more current document values. Each current document value corresponds to one master term and is associated with a current date and a current reference. The current reference identifies a region in the master document related to the one master term. The method further includes selecting a first child term from the one or more first child terms.

Abstract: A system finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: Systems and methods for generating logical documents for a document evaluation system are provided. For example, a method for generating logical documents for a document evaluation system includes receiving a first child document associated with a master document. The master document includes one or more master terms. The first child document includes one or more first child terms and a first date. The method further includes generating a logical document based at least in part on the master document. The logical document includes one or more current document values. Each current document value corresponds to one master term and is associated with a current date and a current reference. The current reference identifies a region in the master document related to the one master term. The method further includes selecting a first child term from the one or more first child terms.

Abstract: System and method for adaptive training of a machine learning system processing textual data. For example, a method for adaptive training of a machine learning system configured to predict answers to questions associated with textual data includes receiving predicted answers to questions associated with textual data. The predicted answers are generated based at least in part on one or more first models of a machine learning system. The one or more first models are associated with a first accuracy score. The method further includes determining based at least in part on a quality control parameter whether an evaluation of the questions by one or more external entities is required. In response to determining based at least in part on the quality control parameter that an evaluation of the questions by one or more external entities is required, the questions associated with the textual data and the textual data are sent to the one or more external entities for evaluation.

Abstract: System and method for dynamically displaying a user interface of an evaluation system configured to evaluate predicted answers generated by a machine learning system. For example, the method includes receiving textual data and a predicted answer to a question associated with a text object. The text object includes a structured data field of the textual data. The predicted answer includes a confidence level. The confidence level is determined by a machine learning system based at least in part on one or more models of the machine learning system and the textual data. In response to determining the confidence level being larger than or equal to a predetermined confidence threshold, the predicted answer and a reference is stored in a storage for retrieval and display. The reference indicates a location of the text object in the textual data.

Abstract: A system finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: A system finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: A system automatically and continuously finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: A system automatically and continuously finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: A system automatically and continuously finds and aggregates the most relevant and current information about the people and things that a user cares about. The information gathering is based on current context (e.g., where the user is, what the user is doing, what the user is saying/typing, etc.). The result of the context based information gathering is presented ubiquitously on user interfaces of any of the various physical devices operated by the user.

Abstract: Systems and methods are disclosed for customizing a user's experience with an application such as a search engine application. The user's experience is customized based on inferring a mood and/or interests of the user at least in part from an analysis of the user's posts on one or more social media sites. The search engine application is configured to include a user-following engine which follows a user's activities on social media websites. By tracking a user's posts and other activity on social media websites, and possibly those of his or her friends, the user-following engine is able to draw inferences about a user, including for example the user's emotional state, current trending interests, future plans, likes/dislikes and aspirations. The user-following engine may then customize the user's search experience based on these drawn inferences.

Abstract: A companion gaming experience is associated with a particular game title, but a user interface for the companion gaming experience is generated by a separate program from the associated game title and is presented on a device separate from the device on which the game user interface itself is presented. When an associated game of the video game title is not running, the companion gaming experience presents guide information and/or statistics data for the game title. However, when an associated game of the game title is running, the companion gaming experience presents gameplay data for the game in near-real-time.

Abstract: A companion gaming experience is associated with a particular game title, but a user interface for the companion gaming experience is generated by a separate program from the associated game title and is presented on a device separate from the device on which the game user interface itself is presented. When an associated game of the video game title is not running, the companion gaming experience presents guide information and/or statistics data for the game title. However, when an associated game of the game title is running, the companion gaming experience presents gameplay data for the game in near-real-time.