Abstract: The present disclosure provides a memory-based neural network for question answering. Embodiments of the disclosure identify meta-evidence nodes in an embedding space, where the meta-evidence nodes represent salient features of a training set. Each element of the training set may include a questions appended to a ground truth answer. The training set may also include questions with wrong answers that are indicated as such. In some examples, a neural Turing machine (NTM) reads a dataset and summarizes the dataset into a few meta-evidence nodes. A subsequent question may be appended to multiple candidate answers to form an input phrase, which may also be embedded in the embedding space. Then, corresponding weights may be identified for each of the meta-evidence nodes. The embedded input phrase and the weighted meta-evidence nodes may be used to identify the most appropriate answer.

Abstract: An input question enhancement mechanism is provided for merging sub-question results in Question and Answer (QA) systems in order to answer an input question submitted from a user. A plurality of sub-questions associated with the input question is identified. Responsive to submitting the set of questions to a QA pipeline of the QA system, a set of answers and a set of passages related to the set of answers corresponding to each of the plurality of sub-questions are received. A mapping is applied to the set of passages to form a consolidated set of passages. The set of answers is then merged into the mapping so as to generate a consolidated set of answers. A factoid question response report is generated with answers from the consolidated set of answers and passages from the consolidated set of passages. The factoid question response report is then provided to the user.

Abstract: A method is provided that includes generating answer-passage pairs, each associated with a respective one of multiple feature vectors. The method includes, for each answer in the pairs, merging the feature vectors associated with any of the pairs that include the answer to obtain a merged answer vector. The method includes, for each passage in the pairs, (i) merging the feature vectors associated with any of the pairs that includes the passage to obtain a merged passage vector, (ii) merging the feature vectors from the merged answer vector for each answer that is associated with the passage via at least one of the pairs to obtain a merged passage-answer vector, and (iii) concatenating the merged passage vector and the merged passage-answer vector to obtain a concatenated passage vector. The method includes ranking the concatenated passage vector for each passage to obtain a ranked list of passages with associated confidence scores.

Abstract: A method, a system, and a computer program product for creating and evaluating assessment sheets are disclosed. The method includes identifying one or more first location identifiers based on one or more markings provided in a scanned master assessment sheet. A machine-readable code (MRC) is generated based on the one or more first location identifiers. The MRC is then split into a plurality of portions and embedded at various locations on a scanned pre-assessment sheet. The scanned pre-assessment sheet with the embedded MRC is then printed to generate the assessment sheets. Thereafter, one or more second location identifiers are identified based on one or more markings provided by evaluatees in each of the assessment sheets provided to them. The one or more second location identifiers are then compared with the one or more first location identifiers. The result of evaluation is provided based on the comparison.

Abstract: Methods/systems receive a question and automatically search sources of data containing passages to produce candidate answers to the question. The searching identifies passages that support each of the candidate answers based on scoring features that indicate whether the candidate answers are correct answers to the question. These methods/systems automatically create a scoring feature-specific matrix for each scoring feature. Each scoring feature-specific matrix has a score field for each different combination of text passage and question term (vector), and each score field holds a score value (vector value) indicating how each different combination of text passage and question term supports the candidate answers as being a correct answer to the question. Next, such methods/systems automatically combine multiple such vectors to produce a combined vector score for each of the candidate answers, and then rank the candidate answers based on the combined scores.

Abstract: The present subject matter relates to a method for customized question paper generation. The method includes assigning at least one key value to each of a plurality of questions, and storing the questions along with the at least one associated key value in a question bank. The method further includes fetching the stored questions based on rules in a question paper template, where the rules are based on the at least one key value. Furthermore, the method includes validating the fetched questions based on at least one constraint and generating the question paper based on the validating.

Abstract: A computer-implemented method for publishing a user credential includes receiving a score regarding at least one capability of an individual, wherein the score is based at least on a plurality of test inputs provided by the individual in response to an assessment test; receiving permission, from the individual, to allow publication of a credential certificate on a computer-implemented user profile associated with the individual, wherein the credential certificate is based at least in part on the score and includes at least one interface element for requesting additional information related to the individual; publishing the credential certificate and at least one interface element on the computer-implemented user profile associated with the individual; and providing a link to the additional information in response to a request for the additional information from the authorized employer, wherein the request is based on activation of at least one interface element by the authorized employer.

Abstract: A system and method for automated assessment of constrained constructed responses provides for automatic, e.g., programmatic, assessing of a test subject response to a constrained constructed response item or question. In one embodiment, paper test materials with test subject markings thereon are converted to electronic form. Test subject markings are further isolated, for example, by registration, sizing and removal of markings other than a graphic response. The subject markings are further compared with a baseline response, correctness deviation criteria and incorrectness deviation criteria (e.g., correctness, incorrectness, substantial correctness, substantial incorrectness, and so on) from which one or more of a score, further learning or other assessment results may be determined. Cluster analysis or other post-evaluation or post-assessment processing may also be conducted, or re-evaluation or re-assessment may also be conducted.

Abstract: An interactive book reading system (600) responsive to a human finger presence. The system (600) includes a radio frequency (RF) scanning circuit (675), a control circuit (610), a memory (615) and an audible output device (650). The RF scanning circuit (675) is configured to detect the presence of the human finger when the finger enters an RF field generated by the RF scanning circuit (675). The control circuit (610) and the memory (615) are in communication with the RF scanning circuit (675). The memory (615) stores a plurality of audible messages. The audible output device (650) is also in communication with the control circuit (610). The audible output device (650) outputs at least one of the audible messages based on an analysis of the RF field performed by the control circuit (610) when the finger enters the RF field.

Abstract: A method and system for performing image mark recognition for a document is disclosed. A document is scanned into a digital image. Reference image marks are sensed from the digital image. The reference image marks may include trigger row marks and/or corner/crop marks. Coordinates denoting the location of cells within the digital image are determined base on the locations of the reference image marks. Response marks are evaluated for darkness, opacity, and/or grayness on a pixel-by-pixel basis. The response marks are each assigned a percentage value based on the ratio between a total color value for a cell and a maximum color value for a cell.

Abstract: A method and system for performing image mark recognition for a document is disclosed. A document is scanned into a digital image. Reference image marks are sensed from the digital image. The reference image marks may include trigger row marks and/or corner/crop marks. Coordinates denoting the location of cells within the digital image are determined based on the locations of the reference image marks. Response marks are evaluated for darkness, opacity, and/or grayness on a pixel-by-pixel basis. The response marks are each assigned a percentage value based on the ratio between a total color value for a cell and a maximum color value for a cell.

Abstract: A test form comprises a substrate, a chromogenic material applied to at least a top surface portion of the substrate, a removable opaque layer overlaying a portion of the chromogenic material, the chromogenic material being adapted to irreversibly generate a visible change in color to form a desired indicia, upon exposure of the area to an activating agent such as heat to predetermined areas on a bottom portion of the substrate, all without disturbing the opaque layer covering the indicia so produced. The present invention is further directed to a method and system for customizing a test form having a removable opaque layer, by permitting printing under the opaque layer to be concealed until the corresponding opaque layer covering the indicia is removed.

Abstract: A method for scoring an answer page containing an answer to an open-ended question includes viewing a first visual image of a first portion of an answer page. The first portion contains an answer space in which an answer to an open-ended question is expected to reside. If the first portion of the answer page contains a complete answer, the answer is electronically scored. If the first portion of the answer page does not encompass a complete answer, a second visual image of a second portion of the answer page is accessed and viewed. The second portion contains a sector of the answer page outside the answer space. A method is also provided for delivering an answer page to a reader for scoring.

Abstract: An imaging system includes two sets of cameras: a first set for capturing optical mark or optical character recognition data and a second set for capturing visual images. Full visual images of pages containing answers to open-ended questions are retained and are retrievable by a reader such that an area of interest wherein the answer is expected is displayed, but the remaining area is also available for viewing. The system permits the alignment of a page based upon edge detection if the page contains only an open-ended answer, obviating the need for timing tracks. Hardware and software elements cooperate to store the image temporarily in a server having a response time commensurate with the scanner. The image is then processed with the use of high-performance index imaging for optical storage and retrieval, and then routed to a long-term storage device.

Abstract: This invention is a computer based system for the assessment, management and instruction of students, and for the delivery of work pages and other instructional materials in the form of electronic student workbooks. The computer based assessment of the student produces a student profile including skill gaps or learning objectives. Teacher (20) and student (22) workstations are networked CPUs with pen-based tablet inputs, and displays network with a central processor (10) and data base. A director workstation may also be networked with the central processor. The central processor generates a teacher workbook either directly or with input from the director workstation. The teacher, or teacher and director together, assemble an electronic student workbook containing instructional materials correlated with the student profile. The system tracks useful data such as instructional material (e.g., textbook pages, work sheets, software, simulations, tests, etc.) delivered to students.

Abstract: An imaging system includes two sets of cameras: a first set for capturing optical mark or optical character recognition data and a second set for capturing visual images. Full visual images of pages containing answers to open-ended questions are retained and are retrievable by a reader such that an area of interest wherein the answer is expected is displayed, but the remaining area is also available for viewing. The system permits the alignment of a page based upon edge detection if the page contains only an open-ended answer, obviating the need for timing tracks. Hardware and software elements cooperate to store the image temporarily in a server having a response time commensurate with the scanner. The image is then processed with the use of high-performance index imaging for optical storage and retrieval, and then routed to a long-term storage device.

Abstract: An imaging system includes two sets of cameras: a first set for capturing optical mark or optical character recognition data and a second set for capturing visual images. Full visual images of pages containing answers to open-ended questions are retained and are retrievable by a reader such that an area of interest wherein the answer is expected is displayed, but the remaining area is also available for viewing. The system permits the alignment of a page based upon edge detection if the page contains only an open-ended answer, obviating the need for timing tracks. Hardware and software elements cooperate to store the image temporarily in a server having a response time commensurate with the scanner. The image is then processed with the use of high-performance index imaging for optical storage and retrieval, and then routed to a long-term storage device.

Abstract: An imaging system includes two sets of cameras: a first set for capturing optical mark or optical character recognition data and a second set for capturing visual images. Full visual images of pages containing answers to open-ended questions are retained and are retrievable by a reader such that an area of interest wherein the answer is expected is displayed, but the remaining area is also available for viewing. The system permits the alignment of a page based upon edge detection if the page contains only an open-ended answer, obviating the need for timing tracks. Hardware and software elements cooperate to store the image temporarily in a server having a response time commensurate with the scanner. The image is then processed with the use of high-performance index imaging for optical storage and retrieval, and then routed to a long-term storage device.

Abstract: This invention is a computer based system for the assessment, management and instruction of students, and for the delivery of work pages and other instructional materials in the form of electronic student workbooks. The computer based assessment of the student produces a student profile including skill gaps or learning objectives. Teacher (20) and student (22) workstations are networked CPUs with pen-based tablet inputs, and displays network with a central processor (10) and data base. A director workstation may also be networked with the central processor. The central processor generates a teacher workbook either directly or with input from the director workstation. The teacher, or teacher and director together, assemble an electronic student workbook containing instructional materials correlated with the student profile. The system tracks useful data such as instructional material (e.g., textbook pages, work sheets, software, simulations, tests, etc.) delivered to students.

Abstract: An educational and entertainment device wherein a microcomputer is mounted in a housing to receive user generated data presented by moving a conducting stylus across perpendicular arrays of conductors on a work surface formed on the housing and presents information to the user via audio and visual devices. The conductors of each array are organized into first write groups formed of a plurality of interconnected conductors which can be placed in a selected electrical state by words written to the write groups and into read groups, read by the microcomputer, formed of a plurality of interconnected conductors interspersed with the conductors of the write groups. Additional, second write groups are interspersed with the first write groups and read groups. The arrays are alternatively mounted on the work surface or on a support member which can be detachably mounted on the work surface and connectors are provided for connecting the arrays on the support member to the microcomputer.

Abstract: An interactive electronic game book is disclosed in which the pages of the book form game boards for educational or amusement-type games. An electronic randomizer unit is affixed to the back cover of the game book for providing randomly-selected instructions directing the games and allowing the player to interact with the game board pages. The randomizer unit may sequentially operate and randomly select one of a plurality of lights, which correspond to one of a set of game instructions provided on a page adjacent to the randomizer. Several different types of game boards may be contained within a single volume.