Classification of collections of items such as words, which are called “document classification,” and more specifically explaining a classification of a document, such as a web-page or website. This can include exemplary procedure, system and/or computer-accessible medium to find explanations, as well as a framework to assess the procedure's performance. An explanation is defined as a set of words (e.g., terms, more generally) such that removing words within this set from the document changes the predicted class from the class of interest. The exemplary procedure system and/or computer-accessible medium can include a classification of web pages as containing adult content, e.g., to allow advertising on safe web pages only. The explanations can be concise and document-specific, and provide insight into the reasons for the classification decisions, into the workings of the classification models, and into the business application itself. Other exemplary aspects describe how explaining documents' classifications can assist in improving the data quality and model performance.

Potential linguistic errors within a sequence of words of a sentence are identified based on analysis of a configurable sliding window. The analysis is performed based on an assumption that if a sequence of words occurs frequently enough within a large, well-formed corpus, its joint probability for occurring in a sentence is very likely to be greater than the same words randomly ordered.

Examples of the disclosure describe user environment aware single channel acoustic noise reduction. A noisy signal received by a computing device is transformed and feature vectors of the received noisy signal are determined. The computing device accesses classification data corresponding to a plurality of user environments. The classification data for each user environment has associated therewith a noise model. A comparison is performed between the determined feature vectors and the accessed classification data to identify a current user environment. A noise level, a speech level, and a speech presence probability from the transformed noisy signal are estimated and the noise signal is reduced based on the estimates. The resulting signal is outputted as an enhanced signal with a reduced or eliminated noise signal.

A computer-implemented technique includes techniques are presented for user image capture feedback for improved machine language translation. When machine language translation of OCR text obtained from an initial image has a low degree of likelihood of being an appropriate translation, these techniques provide for user image capture feedback to obtain additional images to obtain a modified OCR text, which can result in improved machine language translation results. Instead of user image capture feedback, the techniques may obtain the modified OCR text by selecting another possible OCR text from the initial OCR operation. In addition to additional image capturing, light source intensity and/or a quantity/number of light source flashes can be adjusted. After obtaining the modified OCR text, another machine language translation can be obtained and, if it has a high enough degree of likelihood, it can then be output to a user.

Different forward-translated sentences are generated by translating a received translation-source sentence in a first language into a second language. Backward-translated sentences are generated by backward-translating the different forward-translated sentences into the first language. When an operation for selecting one of the backward-translated sentences is received during output of the backward-translated sentences on an information output device, the forward-translated sentence corresponding to the selected backward-translated sentence is output onto the information output device.

A method, system and computer program product for enabling attendees of a web conference to view materials of the web conference in their native language. When the conference server determines that the preferred native language of the attendee differs from the preferred native language of the presenter of the web conference, the conference server creates a virtual environment that is a clone of a host environment of the presenter that runs a native language pack of the preferred native language of the attendee. Upon the presenter starting the web conference, the screen shot shared by the presenter to the attendees is captured from the host environment of the presenter and then translated into the preferred native language of the attendee using the native language pack of the attendee's virtual environment. The translated screen shot is then sent to the attendee in the attendee's preferred native language from the virtual environment.

The technology described herein enables users to enrich their vocabulary by annotating and/or automatically translating specific words, which are predicted to be unknown to the specific user. The user experiences the original content enriched with adaptive, smart in-line annotations of unknown words. The technology is tailored to individual users by understanding an individual user's vocabulary in a particular language. As a user consumes content or performs document authoring/editing activities, the system captures language usage patterns, maintained in a private Vocabulary Analytics Store (VAS) for the particular user. Information in the VAS is used as input to a machine classifier that determines whether a word is likely to be known or unknown to a user.

The present teaching relates to obtaining information from a user via a bot. In one example, a request is obtained to collect information in connection with a user. A statement is generated to be expressed to the user for facilitating a conversation between the user and the bot based on the request. Information is received in connection with the user and collected during the conversation. The collected information characterizes the user in a plurality of modalities. The collected information is automatically analyzed in the plurality of modalities to obtain an assessment of one or more human traits of the user. A plurality of result summaries are generated based on the assessment. The plurality of result summaries are provided in response to the request.

Outputs from a graphical user interface of a target computer program are captured during actual use of the target computer program. The captured outputs are processed to recognize strings and associate those strings with content derived from the outputs. The recognized strings and associated content are stored as context data. A translation editing tool accesses the context data and message data of the target computer program. The translation editing tool presents the message data through a graphical user interface to a user. In response to selected text from the message data, the context data are accessed to retrieve content associated with a recognized string that matches the selected text. The retrieved content is presented in the graphical user interface of the translation editing tool to provide contextual information to inform how to translate a message. Text input from the translator can be stored in the message data.

Systems and methods are described herein for performing actions based on a determined intent within messages received by a mobile device. In some embodiments, the systems and methods may access a message received by a mobile application (e.g., text messaging application, chat application, and so on) of the mobile device, analyze the message to determine an intent of the message (e.g., whether the message includes a request or a task for a recipient of the message), and perform an action based on the determined intent (e.g., set a reminder when the message includes a task for the recipient). Further details are described herein.