Abstract: A content analysis system provides content understanding for a content item using an attention aware multi-modal model. Given a content item, feature extractors extract features from content components of the content item in which the content components comprise multiple modalities. A cross-modal attention encoder of the attention aware multi-modal model generates an embedding of the content item using features extracted from the content components. A decoder of the attention aware multi-modal model generates an action-reason statement using the embedding of the content item from the cross-modal attention encoder.

Abstract: A method includes receiving uncompilable code from a candidate. The method further includes extracting features from the uncompilable code. The method further includes outputting, with a coding machine-learning model, compilable code based on the uncompilable code and the extracted features. The method further includes generating a coding score based on the uncompilable code and the compilable code. The method further includes receiving first media of one or more answers to questions provided by the candidate during an interview. The method further includes outputting, with a media machine-learning model, one or more corresponding ratings for the one or more answers. The method further includes generating a media score based on the one or more corresponding ratings. The method further includes generating a total score based on the coding score and the media score.

Abstract: A method may include receiving an electronic message from a sender. The method may further include parsing the electronic message into a set of sections, the set of sections including structured sections and an unstructured section. The method may further include detecting etiquette errors in the structured sections of the electronic message, wherein the etiquette errors include at least one of a missing word, a redundant word, an incorrect usage of a word, a style error, an emotional punctuation error, or a punctuation error. The method may further include generating an etiquette score based on the etiquette errors.

Abstract: A method may include receiving an electronic message from a sender. The method may further include parsing the electronic message into a set of sections, the set of sections including structured sections and an unstructured section. The method may further include detecting etiquette errors in the structured sections of the electronic message, wherein the etiquette errors include at least one of a missing word, a redundant word, an incorrect usage of a word, a style error, an emotional punctuation error, or a punctuation error. The method may further include generating an etiquette score based on the etiquette errors.

Abstract: Disclosed herein are various techniques for more precisely and reliably (a) positioning top and bottom border edges relative to textual content, (b) positioning left and right border edges relative to textual content, (c) positioning mixed edge borders relative to textual content, (d) positioning boundaries of a region of background shading that fall within borders of textual content, (e) positioning borders relative to textual content that spans columns, (f) positioning respective borders relative to discrete portions of textual content, (g) positioning collective borders relative to discrete, abutting portions of textual content, (h) applying stylized corner boundaries to a region of background shading, and (i) applying stylized corners to borders.

Abstract: Disclosed herein are various techniques for more precisely and reliably (a) positioning top and bottom border edges relative to textual content, (b) positioning left and right border edges relative to textual content, (c) positioning mixed edge borders relative to textual content, (d) positioning boundaries of a region of background shading that fall within borders of textual content, (e) positioning borders relative to textual content that spans columns, (f) positioning respective borders relative to discrete portions of textual content, (g) positioning collective borders relative to discrete, abutting portions of textual content, (h) applying stylized corner boundaries to a region of background shading, and (i) applying stylized corners to borders.

Abstract: A method includes receiving uncompilable code from a candidate. The method further includes extracting features from the uncompilable code. The method further includes outputting, with a coding machine-learning model, compilable code based on the uncompilable code and the extracted features. The method further includes generating a coding score based on the uncompilable code and the compilable code. The method further includes receiving first media of one or more answers to questions provided by the candidate during an interview. The method further includes outputting, with a media machine-learning model, one or more corresponding ratings for the one or more answers. The method further includes generating a media score based on the one or more corresponding ratings. The method further includes generating a total score based on the coding score and the media score.

Abstract: A method to generate compilable code from uncompilable code. The method includes receiving uncompilable code. The method further includes generating compilable code by one or more of (1) identifying and correcting syntax errors in the uncompilable code and (2) using an n-gram based token prediction model. The method further includes extracting features from the compilable code. The method further includes generating a machine learning model that recognizes patterns from extracted features in the compilable code.

Abstract: A method may include receiving an electronic message from a sender. The method may further include parsing the electronic message into a set of sections, the set of sections including structured sections and an unstructured section. The method may further include detecting etiquette errors in the structured sections of the electronic message, wherein the etiquette errors include at least one of a missing word, a redundant word, an incorrect usage of a word, a style error, an emotional punctuation error, or a punctuation error. The method may further include generating an etiquette score based on the etiquette errors.

Abstract: Disclosed herein are various techniques for more precisely and reliably (a) positioning top and bottom border edges relative to textual content, (b) positioning left and right border edges relative to textual content, (c) positioning mixed edge borders relative to textual content, (d) positioning boundaries of a region of background shading that fall within borders of textual content, (e) positioning borders relative to textual content that spans columns, (f) positioning respective borders relative to discrete portions of textual content, (g) positioning collective borders relative to discrete, abutting portions of textual content, (h) applying stylized corner boundaries to a region of background shading, and (i) applying stylized corners to borders.

Abstract: A method to generate compilable code from uncompilable code. The method includes receiving uncompilable code. The method further includes generating compilable code by one or more of (1) identifying and correcting syntax errors in the uncompilable code and (2) using an n-gram based token prediction model. The method further includes extracting features from the compilable code. The method further includes generating a machine learning model that recognizes patterns from extracted features in the compilable code.

Abstract: A method for generating a messaging stream that is transmitted over a network to a user device is disclosed. The method includes generating an introductory message. The method further includes receiving an introductory response from the user device. The method further includes providing a first module question to the user device. The method further includes determining whether a first module response that includes one or more words received from the user corresponds to one of a set of recognizable responses stored in a database. The method further includes scoring the first module responses. The method further includes generating a user interface that includes a score of the user responses.

Abstract: A method and system for constructive response grading for spoken language is disclosed. The method and system are computer implemented and involve a crowdsourcing step to derive evaluation features. The method includes steps for posting a speech test through an automated speech assessment tool, receiving candidate responses from candidates for the speech test; delivering the candidate responses to crowdsource volunteers; receiving crowdsourced responses from crowdsource volunteers, where the crowdsourced responses comprise a transcription of the speech test; deriving features from the transcription; and deriving a individual scores based on the features, where the individual scores are representative of pronunciation score, fluency score, content organization score and grammar score of the spoken language for each candidate.

Abstract: A method for selecting a communication channel. The method includes identifying a job, identifying a target for the job, determining a characteristic of the target, obtaining analytic information using the characteristic, identifying, using the analytic information, a first communication channel of a plurality of communication channels over which to send a first job message for the job to the target, wherein a conversion rate associated with the first communication channel is higher than any conversion rate associated with any other of the plurality of communication channels and wherein the conversion rates are determined using the analytic information, and generating the first job message, wherein the first job message is associated with a first URL, and wherein the first URL is associated with the job, a sender, the target, and the first communication channel, and sending the first job message over the first communication channel to the target.

Abstract: A method and system for measuring traits associated with motor skills of a user, and providing a score based on the traits is provided. The method is implemented on a non-transitory computer readable medium is provided. The method includes generating a predictive model comprising a benchmark to score each of the traits representative of motor skills. The method includes configuring test scenarios delivered on a touch based user interface having a communication interface with a processing device. The method includes measuring the traits based on user activity with the test scenarios, comparing the measurements with the corresponding measurements in the predictive model, generating at least one of, one or more scores, and feedback analytics for the traits based on the comparison; and reporting the one or more scores to at least one of the touch based user interface and an external device.

Abstract: A method for identifying a source of a job referral, the method including identifying a URL that the job applicant uses to access a web page with functionality to enable the job applicant to apply for the first job, identifying a first job message record using the URL, obtaining an original job message record for an original job message using the first job message record, determining a first sender of the original job message from the original job message record, determining that a second job message was sent to the job applicant for a second job at the company by a second sender, wherein the second job message was sent to the job applicant before the first job message and wherein the second job message was sent to the job applicant within a look-back period, and identifying the second sender as the source of the referral for the first job.

Abstract: System and method for developing and evaluating situational judgment is disclosed. The method includes the steps of creating content for one or more test situations; creating one or more options to address each of the one or more situations; posting the one or more test situations and one or more options to address each of the one or more situations to an online crowdsourcing platform; receiving responses by the plurality of respondents through the online crowdsourcing platform and normalizing the received responses wherein the normalization is done based on aggregation of responses by the plurality of respondents.

Abstract: The present invention provides a system and methods for extracting features from an object. The system comprises a receiver configured to receive an object comprising a set of instructions. Further, the system comprises an extraction module configured to extract one or more features of the object, wherein the one or more features comprise control-flow information, data-flow information, data-dependency information and control-dependency information. In an embodiment, the system includes an assessment module configured to assess at least one of functionality and quality of the first object, based on the features extracted and the grades corresponding to the second object.

Abstract: The system includes a receiving module configured to receive a first set of data and a second set of data, wherein the first set of data comprises one or more high quality objects, and one or more ungraded objects, wherein the second set of data comprises one or more ungraded objects, an identification module configured to identify the one or more high quality objects, an extraction module is configured to extract one or more features from each high quality object of the one or more high quality objects, a building module is configured to build a predictive model based on the one or more features extracted for the each high quality object, a comparison module configured to compares the one or more ungraded objects and the one or more high quality objects, and an assessment module configured to score the one or more ungraded objects.

Abstract: A method and system for automatic assessment of a person's programming skill has been provided. The method involves gathering an input code from the person in relation to a programming problem statement. The input code is then processed using a processor. One or more scores are determined from the input code based on at least one of a time complexity and taxonomy of test cases.