Abstract: Some examples described herein relate to automatically configuring an insight carousel of a graphical user interface based on templates. In one example, a system can receive templates and insights associated with transactions, populate fields within each template using information associated with the insights, and generate a graphical user interface including an image carousel having slides incorporating the populated templates.

Abstract: Systems and methods for switching between natural language processing units during an interaction using a dialog delegation processor. The method includes receiving a dialog utterance from a user via a user device. The method further includes determining a general intent based on the dialog utterance using a general natural language processor. The method also includes determining at least one specific intent corresponding to the general intent using the general natural language processor. The method also includes selecting a specific natural language processor corresponding to the at least one specific intent. The method further includes determining a dialog response corresponding to the at least one of specific intent using the specific natural language processor. The method also includes generating for display the dialog response on the user device.

Abstract: The present invention relates to a method for reinforcing a multiple-choice QA model based on adversarial learning techniques, wherein incorrect answers are further generated based on a data set used in the process of training the multiple-choice QA model to enrich data which are learnable by the multiple-choice QA model.

Abstract: System and methods for displaying one or more assets on a client device based on device characteristics are provided. Code is transmitted to a client device. The code, when executed by the client device, causes a processor of the client device to determine a first device characteristic of the client device. A first layout may be selected based on the first device characteristic. The layout may include one or more cards. Each card may correspond to one or more assets. Each card may be modified based on a corresponding card characteristic. One or more assets may be requested. The assets may be displayed on the first client device. The code may be transmitted to another client device, which may select a different layout based on a different device characteristic.

Abstract: Methods and systems for identifying anatomical phrases in medical text. Methods and systems described herein use a syntactic approach to generate lists of relevant terms and define a grammar on these terms. Methods and systems described then search for phrases in text that conform to the grammar.

Abstract: Systems and methods are disclosed herein for generating content based on format-specific screenplay parsing techniques. The techniques generate and present content by generating new dynamic content structures to generate content segments for output on electronic devices. In one disclosed technique, a first instance of a first character name is identified from the screenplay document. A first set of character data following the first instance of the first character name from the screenplay document and preceding an instance of a second character name from the screenplay document is then identified. Upon identification of the first set of character data, a content structure including an object is generated. The object includes attribute table entries based on the first set of character data. A content segment is generated for output based on the content structure (e.g., a 3D animation of the first character interacting within a scene).

Abstract: Computer-implemented design tool functions are described herein for automatically performing edits across different portions of one or more design layouts. According to an example, a method includes causing a display device to display a design interface used to edit a design layout, which includes at least a first frame and a second frame. The method includes receiving first input to initiate a multi-edit mode in the design interface and receiving second input to perform a first operation to edit a first node in the first frame. The method further includes identifying, based at least in part on the second input, a second node in the second frame and corresponding to the first node in the first frame. In this example, the method includes performing, based at least in part on the second input, the first operation to edit the first node in the first frame and a second operation to edit the second node in the second frame.

Abstract: A document management apparatus includes a display control unit that performs control to display a first document and a second document, a comment reception unit that receives a comment to be added to a part of the first document displayed by the display control unit, and an association unit that associates a part of the second document that is a basis of the comment received by the comment reception unit with the comment.

Abstract: In some examples, a system for generating a topic model includes a processor that can process a set of documents to generate training data, wherein each document in the set of documents is associated with one or more users. The processor can also generate a plurality of topic models using the training data, such that each topic model includes a different number of topics. The processor can also generate an evaluation score for each of the topic models based on information about the users associated with the documents included in the training data. The evaluation score describes a percentage of topics that exhibit a specified level of interest from a specified number of users. The processor can also identify a final topic model based on the evaluation scores and store the final topic model to be used in natural language processing.

Abstract: A computer executed process for mimicking human dialog, referred to herein as a “humanoid” or “humanoid process software,” can be configured to participate in multi-party conversations. The humanoid can monitor electronic communications in a conversation involving the humanoid and at least one other party. The humanoid can model the electronic communications by uniquely identifying each of the electronic communications as a stream of data. For example, the data can be labeled and sorted in a database and/or arranged in a nodal graph representation. The humanoid can participate in the conversation based on the modeling.

Abstract: A computer implemented method includes receiving embedded font text defining characters associated with an original font family. The embedded font text is processed to generate original glyph metrics data, a combined original font glyph width based on the original glyph metrics data, and one or more candidate font families are identified. For each candidate font family a combined candidate font family glyph width is calculated and a candidate font family difference, the candidate font family difference being a measure of how the candidate font family's combined candidate font family glyph width compares to the combined original font glyph width. A particular candidate font family is selected as a replacement font family based on the candidate font family differences of the one or more candidate font families.

Abstract: A conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. The conversation engine loads a chatbot configuration that specifies the behavior of a chatbot including the tasks that can be performed by the chatbot, the types of entities relevant to each task, and so on. The conversation may be voice based and use natural language. The conversation engine may load different chatbot configurations to implement different chatbots. The conversation engine receives a conversation engine configuration that specifies the behavior of the conversation engine across chatbots. The system may be a multi-tenant system that allows customization of the chatbots for each tenant.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that merge separate digital point text objects into a single merged digital text object while preserving the properties and original visual appearance associated with the digital text included therein. For example, the disclosed systems can determine point text character properties associated with the separate digital point text objects (e.g., rotations, baseline shifts, etc.). The disclosed systems can merge the separate digital point text objects into a single merged digital point text object and modify associated font character properties to reflect the determined point text character properties. Further, the disclosed systems can generate an area text object based on the merged digital point text object where the area text object includes the digital text and the font character properties.

Abstract: A method retrains a cognitive interaction information system. One or more processors monitors an interactive communication between a user and the cognitive interactive information system. The processor(s) identifies an incorrect answer returned by the cognitive interactive information system to a question asked by the user; reevaluates the question utilizing alternative intent classifications to form alternative answers; and presents the alternative answers to the user. The processor(s) receive a selection from the alternative answers from the user; updates processing rules to generate updated processing rules that are based on the selection; and retrains the cognitive interaction information system based on the updated processing rules.

Abstract: Disclosed subject matter benchmarks and aligns content with target audiences. A user may provide content to a language intelligence platform. Scores are then generated by analyzing the content based on values-specific dictionaries, which reflect values of targeted audiences. Based on a comparison between a generated score and a benchmark values score for the target audience, appropriate action may be taken. Disclosed teachings support multiple layers of comparisons and score calculations including comparisons and scoring of all text, segments of text, and specific phrases to achieve a more comprehensive analysis. Embodiments may determine whether headers or other sections that may garner more attention, are aligned with a benchmark.

Abstract: A method of guided collaborative digital contract drafting and negotiations using a chatbot and/or virtual assistant to guide a user through developing a digital contract. The chatbot provides a user with an interactive guided process through a collaborative digital contract drafting process by allowing a natural language interaction. The chatbot can provide education to the user, explain the process and different portions of the digital contract, and offer suggestions for substitute clauses. Furthermore, the user can interact with the chatbot to navigate through the process as well. Additionally, depending on the industry and the purpose of the digital contract, the chatbot can suggest other parties to involve and coordinate communications.

Abstract: A symbol sequence converting apparatus according to an embodiment includes one or more hardware processors. The processors: generates a plurality of candidate output symbol sequences, based on rule information in which input symbols are each associated with one or more output symbols each obtained by converting the corresponding input symbol in accordance with a predetermined conversion condition, the plurality of candidate output symbol sequences each containing one or more of the output symbols and corresponding to an input symbol sequence containing one or more of the input symbols; derives respective confidence levels of the plurality of candidate output symbol sequences by using a learning model; and identifies, as an output symbol sequence corresponding to the input symbol sequence, the candidate output symbol sequence corresponding to a highest confidence level.

Abstract: In response to determining that a particular sequence of natural language input has been generated by a first entity participating in a multi-interaction dialog, a first representation of accumulated dialog state associated with the sequence is obtained from a machine learning model at an artificial intelligence service. Based on the first representation, a state response entry is selected from a collection of state response entries. The state response entry indicates a mapping between a second representation of accumulated dialog state, and a response recorded in a training example of the model. The recorded response is implemented.

Abstract: Techniques for customizing multimedia content using data structures adapted to text samples. A method includes dividing a text sample into segments. Unique words are identified within the segments. For each unique word found in the segments, its neighboring words are identified. Based on sentiment values associated with those neighboring words, a sentiment of each unique is determined. Using the sentiments of the unique words, text skeletons are modified by inserting the unique words into corresponding locations within structured data of the text skeletons. The modified text skeletons may be inserted into multimedia content in order to customize that multimedia content to the text sample.

Abstract: A mechanism is described for facilitating multiple multimedia viewing planes in media display systems according to one embodiment of the invention. A method of embodiments of the invention includes using a plurality of multimedia planes corresponding to a plurality of multimedia content types. The plurality of multimedia planes may be integrated to be presented through an integrated user interface at a media processing device. The method may further include selecting, via the integrated user interface, one or more content categories from a plurality of multimedia content categories, and presenting, via a multimedia plane of the plurality of multimedia planes, contents associated with the one or more selected content categories.