Abstract: The present embodiments provide visual search techniques which produces results that include both accurate similar items as well diversified items through attribute manipulation. In some embodiments, a feature vector describing the item of interest is obtained. A target feature vector is then generated at least partially from the original feature vector, in which the target feature vector shares only a subset of attribute values with the original feature vector and includes at least some values that are different from the original feature vector. An electronic catalog of items is then queried using the target feature vector, and a set of candidate items are determined from the electronic catalog based at least in part on similarity to the target feature vector. The original feature vector may be used to query for a set of similar items that are as similar as possible to the item of interest.

Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, to facilitate identification of additional trigger-terms for a structured information card. In one aspect, the method includes actions of accessing data associated with a template for presenting structured information, wherein the accessed data references (i) a label term and (ii) a value. Other actions may include obtaining a candidate label term, identifying one or more entities that are associated with the label term, identifying one or more of the entities that are associated with the candidate label term, and for each particular entity of the one or more entities that are associated with the candidate label term, associating, with the candidate label term, (i) a label term that is associated with the particular entity, and (ii) the value associated with the label term.

Abstract: A data intake and query system may store raw machine data that includes location information. A client system may include a user interface for searching the data intake and query system. The user interface allows a user to define a field search query and to define one or more ad-hoc boundary regions on a map. A combined query is transmitted to the data intake and query system, the combined query including both the field search query and location search information that is based on the ad-hoc boundary regions. The data intake and query system runs the combined query and returns responsive results, which are displayed at the client user interface.

Abstract: A moment engine is arranged to characterize and/or determine relationships between items, such as a wine, or moments, such as an event, emotional experience and/or an activity. Characteristics for the items or moments may be used to define how the items or moments relate to a two-dimensional grid, e.g., to allow the items or moments to be displayed on an X-Y grid. Relationships between items and/or moments can be determined based on the item/moment characterization on the X-Y grid, e.g., to allow for the recommendation of an item for a particular moment, or the recommendation of a moment for a particular item.

Abstract: A user selection assistance apparatus includes: a registration unit that registers information of a plurality of users, which includes biometric features of the respective users, in advance and creates a list; a biometric detection unit that newly detects a current biometric feature of one user; a determination unit that compares the biometric feature that is detected to the biometric features that are registered, and determines a degree of similarity therebetween; a user choosing unit that chooses, from the list, one or more registered users having a biometric feature the degree of similarity of which satisfies a predetermined reference and creates a chosen user list; a display unit that displays the chosen user list; an input unit that receives selection of a specific registered user from the chosen user list; and an execution processing unit that executes predetermined processing when the input unit receives the selection of the specific registered user.

Abstract: A method includes seed expansion using Graph Neural Network (GNN). The method includes retrieving a first plurality of seed accounts based on a first user input indicative of domain-specific information associated with the first plurality of seed accounts. The method further includes determining a second plurality of seed accounts based on the first plurality of seed accounts associated with the domain-specific information, for training a GNN. The method further includes updating the retrieved first plurality of seed accounts and the determined second plurality of seed accounts based on the trained GNN. The method further includes generating a final set of seed accounts associated with the domain-specific information, based on an application of a predefined ranking criteria on the updated first plurality of seed accounts and the second plurality of seed accounts. The method further includes controlling a display screen to output the generated final set of seed accounts.

Abstract: In accordance with an example embodiment, large scale category classification based on sequence semantic embedding and parallel learning is described. In one example, one or more closest matches are identified by comparison between (i) a publication semantic vector that corresponds to at least part of the publication, the publication semantic vector based on a first machine-learned model that projects the at least part of the publication into a semantic vector space, and (ii) a plurality of category vectors corresponding to respective categories from a plurality of categories.

Abstract: A method and system provide areas with lifestyle preferences selected by a user. Generally, a computing device receives a selection of one or more lifestyle preferences from the user. In response to the selected lifestyle preferences, a visual display of one or more areas of a geographic map that includes one or more of the lifestyle preferences that favorably compare to the lifestyle preferences of the user is presented to the user via a user interface of the computing device. Additionally, the user may submit a review of the lifestyle preferences available in a particular location.

Abstract: A method, system and a computer program product are provided for generating a natural language model that is substantially independent of languages and domains by transforming monolingual embeddings into a multilingual embeddings in a first shared embedding space using a cross-lingual learning process, and then transforming the multilingual embeddings into cross-domain, multilingual embeddings in a second shared embedding space using a cross-domain learning process, where the multilingual embeddings and/or cross-domain, multilingual embeddings are evaluated to measure a degree to which the embeddings associate a set of target concepts with a set of attribute words.

Abstract: A method, a computer program product, and a computer system selectively obfuscate a reaction during a communication session. The method includes determining a predicted sentiment for a user who is a participant in a communication session based on a topic being discussed in the communication session. The method includes determining a predicted expression for a reaction to be exhibited by the user based on sensory inputs received from the user while the topic is being discussed. The method includes determining an intent of the reaction based on the predicted sentiment and the predicted expression. The method includes determining a reward score of the reaction based on a type of the reaction and a context of the communication session while the predicted expression is to be exhibited. The method includes rendering a mask over the user based on at least one of the intent and the reward score.

Abstract: In one implementation, systems and methods are provided for developing a computer-implemented digital experience application having a first and a second micro-application. Each micro-application includes a front end interface configured to receive and display information. The first micro-application includes a first event manager configured to detect an application event belonging to a category, and a first state manager configured to detect an application state belonging to the category. The digital experience application further includes a driver application configured to host the first and second micro-applications, an event hub configured to receive the detected application event from the first micro-application, and a state store configured to store the detected application state received from the first micro-application.

Abstract: A system is provided, which may comprise: a word vector database configured to store word vectors, each of the word vectors representing a word or a phrase; a text database configured to store text data; and a processor configured to: receive a user input including a first term; obtain, for each word vector that is stored in the word vector database and that represents a word or a phrase other than the first term, a similarity between that word vector and a word vector representing the first term; select at least one second term based on the obtained similarity; perform a search in the text database using the at least one second term as a query for the search; and provide results of the search.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing a virtual consultant. The methods, systems, and apparatus include actions of obtaining a set of training data that indicates raw topics that are indicative of the set of topics, training a model to identify raw topics relevant to a set of topics, the set of topics associated with one or more digital documents, identifying, within at least one of the digital documents and with the model, raw topics that correspond to the set of topics, determining, for each identified raw topic, a frequency that the raw topic appears in the digital document, determining, for each of the identified raw topics, a topic that corresponds to the raw topic, determining, for each of the topics of the set of topics, a topic score, and providing an indication of the topic scores for the digital document.

Abstract: A computer-implemented method, according to one embodiment, includes: collecting information which corresponds to internet browsing activity, receiving a request to create a bookmark for a first website, and creating keyword and density pairs (KDPs) for the first website using the information collected prior to receiving the request to create the bookmark. Creating the KDPs includes: extracting a plurality of keywords from the first website, and calculating a density value for each of the plurality of keywords based on the information collected prior to receiving the request to create the bookmark. Furthermore, each keyword and respective density value are added to a hash map as a KDP entry. Other systems, methods, and computer program products are described in additional embodiments.

Abstract: Embodiments of the present disclosure disclose a method, apparatus, server and storage medium for image retrieval. The method includes: identifying a plurality of groups of images having identical contents from images on all webpages; aggregating, for each image group, image-related texts on all source webpages of each image to obtain text descriptions of each image group; establishing an inverted index for each image in the image groups based on the text descriptions of the image group, the inverted index at least including, for each text description, source webpages corresponding to all text descriptions of the image group of the text description; and performing image retrieval based on an inputted query and the inverted index.

Abstract: Systems and methods of distributing replicas within a data center are disclosed. A replica distribution scheme for one or more shards is received. The replica distribution scheme indicates a number of replicas of the one or more shards to be distributed within a data center. The data center comprises a plurality of hosts divided into at least a first hierarchical level and a second hierarchical level. A usage score is calculated for a plurality of nodes in the first hierarchical level of the data center and the plurality of nodes is sorted in the first hierarchical level based on the calculated usage score. A set of replicas is distributed to one or more of the plurality of nodes within the first hierarchical level based on the sorting of the plurality of nodes.

Abstract: A processing device receives a dataset comprising a plurality of data points, wherein each data point of the plurality of data points comprises a representative vector for the data point and an associated classification for the data point. The processing device determines, for the dataset, a score representative of a degree of clustering of the plurality of data points. The processing device determines a suitability of the dataset for use in machine learning based on the score.

Abstract: In an example, Virtual Machine (VM) attributes of a first VM are received. First VM data corresponding to the first VM is to be moved from a first cluster of nodes in which the first VM data is stored. Further, a movement value of the first VM is determined based on a movement model and the VM attributes of the first VM. The movement model indicates a dependence of movement value of a VM on VM attributes of the VM. The movement value of the first VM is indicative of a rank order for movement of the first VM data among a plurality of sets of VM data to be moved, where each set of VM data corresponds to a VM.

Abstract: Methods and systems for data quality evaluation are disclosed. A method includes: receiving, by a computing device, at least one data set and a list of rule expressions to bind; building, by the computing device, candidate binding combinations between columns of the at least one data set and variables of each rule expression in the list of rule expressions; building, by the computing device, a new bound rule expression candidate based on the candidate binding combinations; generating, by the computing device, a new bound rule expression based on the new bound rule expression candidate and a data transformation applied to at least one of the columns of the at least one data set; and storing, by the computing device, the new bound rule expression.

Abstract: A method and a system for ranking a document in response to a query, the document having no value for a given feature with respect to the query. A set of documents relevant to the query is generated. The document is selected, and a set of past queries having presented the document as a search result are retrieved. Respective values for the given feature for the document with respect to the set of past queries are retrieved. A respective similarity parameter is determined between the query and each of the set of past queries. The value of the given feature for the document is generated based at least in part on the respective similarity parameter and the respective value for the given feature of at least one past query. The set of documents including the document is ranked based in part on the given feature.

Abstract: Generating a natural language text response to a user query is provided. Sentiment attributes of the user query are encoded into qubits as particle spins. The particle spins in encoded sentiment qubits are observed to generate spin data. A sentiment value is derived for each sentiment key term of the user query based on the generated spin data. A total sentiment of the user query is determined by combining derived sentiment values corresponding to each sentiment key term of the user query. A natural language text response to the user query is generated based on the determined total sentiment of the user query. The natural language text response is transmitted to a client device via a network.

Abstract: A system and method for calculating quality score for digital content are provided. In example embodiments, a first graph is generated comprising a user node and an article node, the user node corresponds to a user and the article node corresponds to an article. An edge is generated between the user node and the article node in the first graph based on a first action. A second graph is generated comprising the user node and the article node. An edge is generated between the user node and the article node in the second graph based on a second action type. A first authority score is calculated for the article node within the first graph. A second authority score is calculated for the article node within the second graph. A quality score is calculated for the article.

Abstract: A wire web component may be included in a graphical user interface (GUI) being presented on a display device. The wire web component may include one or more data fields that are each associated with a respective data value. A designated node representing the designated wire web component may be removed from a wire web component graph that includes a plurality of nodes. Each of the data fields may be associated with a respective API in the wire web component graph. A document object model (DOM) tree stored in memory may be updated to remove the designated wire web component. The GUI presented on the display device may be updated based on the updated DOM tree.

Abstract: A system and method compares an image of an object of interest captured by an image capturing device from a first positional view relative to the object of interest against each of a plurality of images of each of a plurality of reference objects wherein each of the plurality of images of each of the plurality of reference objects is reflective of a unique positional view of the corresponding one of the plurality of reference objects to determine a second positional view relative to the object of interest at which the image capturing device is to be positioned to capture a further image of the product of interest.

Abstract: Embodiments of the present disclosure relate to generation of sentence representation. In an embodiment, a method is disclosed. According to the method, a sentence graph is generated from a sentence containing words, the sentence graph comprising nodes representing the words and edges connecting the nodes to indicate relationships between the words. Word representations for the plurality of words are determined based on the sentence graph by applying a graph convolution operation on respective sets of neighbor nodes for respective ones of the nodes, a set of neighbor nodes for a node having edges connected with the node. A sentence representation for the sentence is determined based on the word representations for use in a natural language processing task related to the sentence. In other embodiments, a system and a computer program product are disclosed.

Abstract: Methods, systems, and computer-readable media are provided for collective reconciliation. In some implementations, a query is received, wherein the query is associated at least in part with a type of entity. One or more search results are generated based at least in part on the query. Previously generated data is retrieved associated with at least one search result of the one or more of search results, the data comprising one or more entity references in the at least one search result corresponding to the type of entity. The one or more entity references are ranked, and an entity result is selected from the one or more entity references based at least in part on the ranking. An answer to the query is provided based at least in part on the entity result.

Abstract: A system and method for processing and actionizing structured and unstructured experience data is disclosed herein. In some embodiments, a system may include a natural language processing (NLP) engine configured to transform a data set into a plurality of concepts within a plurality of distinct contexts, and a data mining engine configured to process the relationships of the concepts and to identify associations and correlations in the data set. In some embodiments, the method may include the steps of receiving a data set, scanning the data set with an NLP engine to identify a plurality of concepts within a plurality of distinct contexts, and identifying patterns in the relationships between the plurality of concepts.

Abstract: An information providing system includes an information providing device and a vehicle. The information providing device includes an acquisition unit configured to acquire second information indicating a candidate point matching first information and evaluation of the candidate point and a second information transmitting unit configured to transmit the second information to the vehicle. The first information indicates a condition for searching for a point at which the vehicle stops when the vehicle is stopped and used for resting. The vehicle includes a second information receiving unit configured to receive the second information from the information providing device and an output unit configured to output the second information.

Abstract: A computer system evaluating an input segment of a communication, in parallel, by a baseline classification model trained with baseline passages indicating dictionary meaning and multiple generative sequence models each trained to classify a particular passage from among multiple indirect passages indicating usage with an indirect meaning, to receive a separate score from the baseline classification model and each of the generative sequence models, each separate score indicating a classification probability for the input segment. The computer system, responsive to one or more particular scores generated by one or more of the generative sequence models exceeding a baseline score generated by the baseline classification model summed with a tuning factor, flagging the input segment as having a potentially indirect meaning.

Abstract: Predicting entities for database query results are described. A system receives a query that includes a query term. The system outputs a query result that identifies at least one record that includes the query term. The system identifies a selection of a record that is identified by the query result and that includes the query term. The system stores information that associates the query term with an entity that corresponds to the selected record. The system scales the information that associates the query term with the entity. The system receives another query that includes the query term. The system outputs another query result in response to the other query, the other query result being based on the scaled information that associates the query term with the entity.

Abstract: Techniques for the automatic semantic analysis and comparison of chatbot capabilities are disclosed. A first chatbot specification associated with a first chatbot is obtained that includes a first plurality of characteristics arranged in a plurality of categories. A second chatbot specification associated with a second chatbot is obtained that includes a second plurality of characteristics arranged in the plurality of categories. One or more differences between the first plurality of characteristics and the second plurality of characteristics for each of the plurality of categories are identified based at least in part on the first plurality of characteristics and the second plurality of characteristics. A natural language expression corresponding to the identified one or more differences is generated and presented to a user via a graphical user interface.

Abstract: Provided are an image extraction apparatus and an image extraction method of finding a similar image conforming to a user's intention. A similarity determination condition designation window in which a plurality of similarity determination conditions are displayed is displayed. A user selects a desired similarity determination condition from among the plurality of similarity determination conditions displayed in the displayed similarity determination condition designation window. The user can determine a similarity determination condition, and can thus find a similar image conforming to the user's intention.

Abstract: A computer system generates a similarity-optimized hierarchy for hierarchical data to improve data access performance and content discovery. An example method includes receiving hierarchical data in an original hierarchy having a plurality of nodes and a depth of d, generating a respective embedding for each node of the plurality of nodes, and determining, for each node of the plurality of nodes, respective k-nearest neighbors based on the respective embedding. Starting with nodes at depth din the original hierarchy, the method includes generating sibling groups, each sibling group having at least one node at depth d, identifying, for each node at depth d, a similarity-optimized parent from depth d?1, and associating each node at depth d with its respective similarity-optimized parent in a similarity-optimized hierarchy. The method also includes completing the similarity-optimized hierarchy by repeating the generating, identifying and associating with nodes at depth d?1 until reaching the hierarchy root.

Abstract: Linguistic analysis methods and computer system for intelligently interacting with users in voice or text mode. The methods can improve the accuracy in recognizing user's physical or mental state when receiving user input expressions that are not in the form of a request or command, but in the form of a narrative or conversational statement, and generate relevant responses that address the user's needs, and perform tasks for the user when possible. The methods analyze the syntactic, semantic, and contextual attributes of terms in the user expressions, and handles ambiguous entities that may be the source of an intended action, or the target of such actions. Specially, methods for recognizing target entities represented by multi-word complex phrases are described and applied thus more appropriate machine responses can be determined when the input expression involves various types of attributes and different degrees of ambiguities.

Abstract: The present disclosure provides a method of training a descriptive text generating model, and a method and apparatus for generating a descriptive text, wherein the method of training a descriptive text generating model comprises: obtaining training data, the training data comprising: a notional word, a first descriptive text and a second descriptive text of the notional word, wherein the second descriptive text is a concise expression of the first descriptive text; regarding the notional word and the first descriptive text of the notional word as input of a seq2seq model, regarding the second descriptive text of the notional word as output of the seq2sequ model, and training the seq2seq model to obtain a descriptive text generating model. The descriptive text generating model according to the present disclosure can implement generation of a concise descriptive text with respect to the notional word in a deep understanding manner.

Abstract: Techniques for generating interest embedding vectors are disclosed. In some embodiments, a system/process/computer program product for generating interest embedding vectors includes aggregating a plurality of web documents associated with one or more entities, wherein the web documents are retrieved from a plurality of online content sources including one or more websites; selecting a plurality of tokens based on processing of the plurality of web documents; and generating embeddings of the selected tokens in an embedding space.

Abstract: Provided are a model processing method and apparatus, and a machine-readable medium, for evaluating a semantic model to be evaluated of a target production system. In an embodiment, the method includes: acquiring feature information for describing a feature of a reference semantic model of at least one other production system; evaluating, on the basis of the feature information acquired, precision of the semantic model to be evaluated. The solution provided in an embodiment of the present invention realizes evaluation of the precision of a semantic model.

Abstract: Systems and methods are provided to compare a target sample of text to a set of textual records, each textual record including a sample of text and an indication of one or more segments of text within the sample of text. Semantic similarity values between the target sample of text and each of the textual records are determined. Determining a particular semantic similarity value between the target sample of text and a particular textual record of the corpus includes: (i) determining individual semantic similarity values between the target sample of text and each of the segments of text indicated by the particular textual record, and (ii) generating the particular semantic similarity value between the target sample of text and the particular textual record based on the individual semantic similarity values. A textual record is then selected based on the semantic similarities.

Abstract: A self-learning natural-language generation (NLG) system receives raw data from Internet-of-Things sensors or other data sources and a set of natural-language reports previously generated from the raw data by a legacy report-generation mechanism. The system divides the reports into two groups that are distinguished by differences in temporal characteristics of the reports or of the raw data from which each report is generated. The system performs a diachronic linguistic analysis that correlates values of the temporal characteristics with differences between linguistic features of each report group's natural-language text. The system creates translation rules that instruct the NLG system how to reproduce these differences and uses the rules to translate the raw data into its own natural-language reports.

Abstract: A method and system for improving a network search query is provided. The method includes receiving a natural language Internet search request and executing a real time search with respect to a database associated with an Internet based search for specified digital information. Categories associated with the natural language Internet search request are identified and associated intent information is received. Digital attributes data identified during the real time search are identified and an associated concept is extracted. The associated concept is mapped to the digital attributes and search based software code is generated and executed. Resulting relevant results are presented and the database is configured such that the relevant results are stored within a logical partition of the database.

Abstract: A search engine provides customized search results in response to a search query using a group search ranker. The customized search results may be determined for a user based on the user's association with a user group having common preferences. Preferences for users may be learned through historical user information that includes interactions by users with websites on the Internet. Users may be grouped based on these preferences, and the user group may have an associated group search ranker. When the user enters a search query at a search engine, the search engine may identify a user group and retrieve the group search ranker. The group search ranker may be used to rank relevant search results identified based on the search query. The ranked search results may be provided for presentation to a user at a user computing device.

Abstract: Methods and systems for creating a memory recall composite for a face and name association image are described. A first image comprising at least a portion of a subject's face may be received. The first image may be analyzed to determine a set of facial features. A set of objects may be determined and displayed using a set of visual and auditory correspondence rules. An association between a graphical representation of the object and a facial feature may be received. A second image or a memory recall composite may be generated that displays at least a portion of the first image using the graphical representation of the object based in part on the association between the graphical representation of the object and the facial feature associated with the subject's face.

Abstract: Aspects of the present invention disclose a method for identifying a relationship between objects of a NoSQL database based on queries of an application programming interface (API) call. The method includes one or more processors identifying an API call that includes two or more NoSQL query requests. The method further includes determining a class for the two or more NoSQL query requests of the API call. The method further includes determining whether a query value of the first NoSQL query request of the API call is present in a second NoSQL query request. The method further includes determining a relationship between the first NoSQL query request and the second NoSQL query request of the API call. The method further includes creating a view in a relational model database based on the respective determined classes for the two or more NoSQL query requests of the API call and the determined relationship.

Abstract: An information processing system, an information processing device, an information processing method, and a storage medium are provided that can extract group terminals from among a plurality of surrounding information processing terminals that have been detected, and calculate a degree of happiness in a surrounding area. The information processing system includes a communication unit configured to receive identification information from a detection device that detects the identification information of a surrounding terminal device, and a control unit configured to extract, as group terminal devices, a plurality of pieces of identification information that are received by the communication unit and indicate a plurality of terminal devices detected by the detection device within a predetermined time, and to calculate a degree of happiness around the detection device in accordance with an extraction result.

Abstract: Disclosed are various embodiments for predicting repeated behavior by an entity with respect to a particular item. In some embodiments, an entity requesting results to a search query may be redirected to an alternative network page associated with the particular item instead of a search results page according the expectation of repeated behavior.

Abstract: An information processing method and apparatus, where the method includes: obtaining a user information table; creating, based on the user information table, a bitmap index including a plurality of bitmap vectors; creating a user identifier array based on the user information table; receiving a query request sent by a client; querying the user information table based on the bitmap index, the user identifier array, and at least one attribute value, to obtain a query result; and sending the query result to the client. In the foregoing manner, second-level indexing for an ad hoc query can be implemented.

Abstract: An approach is provided in which an information handling system identifies candidate answers from a knowledge base that correspond to a question comprising a lexical answer type (LAT). The information handling system determines sub-LATs corresponding to the LAT in a database that are child LATs of the LAT. The information handling system then identifies a set of the candidate answers that correspond to at least one of the sub-LATs and ranks the set of candidate answers based on one or more ranking criterion. In turn, the information handling system provides the ranked set of candidate answers to a user.

Abstract: A categorization analysis system is provided. The categorization analysis system includes one or more hardware processors, a memory including a first plurality of listings categorized in a first target category, and a categorization analysis engine executing on the one or more hardware processors. The categorization analysis engine is configured to determine a label for each listing including performing a search on title, select a set of training listings based on the determined labels, train a first model using the set of training listings and the determined labels, the first model being a classification model configured to classify categorization of listings, identify a suspect listing categorized in the first target category, apply the suspect listing to the first model, thereby generating a categorization result for the suspect listing, the categorization result indicating miscategorization of the suspect listing, and identify the suspect listing in the memory as miscategorized.

Abstract: Person-centric multi-channel opinion mining is performed in a single data repository, such as a data lake. An exemplary method comprises obtaining multi-channel heterogeneous data from a plurality of channels; identifying entities that are targets of opinion information across the plurality of channels; extracting a plurality of user identities from the plurality of channels; aligning the plurality of extracted user identities across the plurality of channels to link common user identities; identifying the entities that are targets of the opinion information of the extracted user identities; linking opinion information of the extracted user identities with a user identity associated with an opinion holder that expressed the opinion information; determining whether the opinion information comprises a positive or negative opinion; and providing a summary of the opinion information of a given opinion holder.

Abstract: Sentiment scores for a first set of text can be normalized based on a statistical measure of sentiment of a corpus of text authored by a set of authors having respective personality profiles similar to a personality profile of an author of the first set of text. The set of authors can be grouped in a first cluster based on a range of at least one metric of a personality profile. A plurality of respective sentiment scores for portions of the corpus can be generated for the first cluster. A statistical measure of the plurality of respective sentiment scores can be generated. The plurality of respective sentiment scores can be normalized based on the statistical measure. The plurality of respective normalized sentiment scores can be applied to the first set of text to generate one or more sentiment scores for the first set of text.