Abstract: A computer-implemented method is provided for estimating output confidence of a black box Application Programming Interface (API). The method includes generating paraphrases for an input text. The method further includes calculating a distance between the input text and each respective one of the paraphrases. The method also includes sorting the paraphrases in ascending order of the distance. The method additionally includes selecting a top predetermined number of the paraphrases. The method further includes inputting the input text and the selected paraphrases into the API to obtain an output confidence score for each of the input text and the selected paraphrases. The method also includes estimating, by a hardware processor, the output confidence of the input text from a robustness of output scores of the input text and the selected paraphrases.

Abstract: A computer-implemented method is provided for estimating output confidence of a black box Application Programming Interface (API). The method includes generating paraphrases for an input text. The method further includes calculating a distance between the input text and each respective one of the paraphrases. The method also includes sorting the paraphrases in ascending order of the distance. The method additionally includes selecting a top predetermined number of the paraphrases. The method further includes inputting the input text and the selected paraphrases into the API to obtain an output confidence score for each of the input text and the selected paraphrases. The method also includes estimating, by a hardware processor, the output confidence of the input text from a robustness of output scores of the input text and the selected paraphrases.

Abstract: A method is provided for determining support of a hypothesis by opinion sentences. The method converts sentence structures in the opinion sentences using various sentence structure conversion methods to obtain converted opinion sentences. For each converted opinion sentence, the method calculates a difference between a proximity label value indicating proximity to the hypothesis and an intermediate score before and after a conversion, adopts the conversion responsive to a condition being met relative to the difference, and adopts the opinion sentence instead responsive to the condition being unmet. The method creates sub-opinions using the various methods applied to adopted conversions and opinion sentences, and obtains an intermediate score for each sub-opinion.

Abstract: A computer-implemented method, apparatus, and computer program product for evaluating a page in a website are provided. The method includes obtaining a link structure of the website. The method also includes identifying a page set, the page set being a set of pages linked to a specific page in the website. The method further includes calculating a degree of dispersion of the page set in the link structure. The method also includes evaluating the specific page using the degree of dispersion to generate a score for the specific page.

Abstract: A computer-implemented method is provided for estimating output confidence of a black box Application Programming Interface (API). The method includes generating paraphrases for an input text. The method further includes calculating a distance between the input text and each respective one of the paraphrases. The method also includes sorting the paraphrases in ascending order of the distance. The method additionally includes selecting a top predetermined number of the paraphrases. The method further includes inputting the input text and the selected paraphrases into the API to obtain an output confidence score for each of the input text and the selected paraphrases. The method also includes estimating, by a hardware processor, the output confidence of the input text from a robustness of output scores of the input text and the selected paraphrases.

Abstract: A method is provided for determining support of a hypothesis by opinion sentences. The method converts sentence structures in the opinion sentences using various sentence structure conversion methods to obtain converted opinion sentences. For each converted opinion sentence, the method calculates a difference between a proximity label value indicating proximity to the hypothesis and an intermediate score before and after a conversion, adopts the conversion responsive to a condition being met relative to the difference, and adopts the opinion sentence instead responsive to the condition being unmet. The method creates sub-opinions using the various methods applied to adopted conversions and opinion sentences, and obtains an intermediate score for each sub-opinion.

Abstract: A method, a computer system, and a computer program product for selecting electronic documents based on an expertness level for a target keyword. The method includes identifying a Lowest Common Ancestor (LCA) for each pair of categories to which documents in a document set belong based on a graph having edges which define relationships between nodes representing respective ones of the categories, the document set being associated with a target keyword, obtaining a degree of dispersion of the categories based on respective distances between the categories of each pair and the corresponding LCA, determining an expertness level for the target keyword based on the degree of dispersion, and in response to receiving a search query including the target keyword, selecting one or more documents from a database based on the expertness level for the target keyword.

Abstract: Text analysis includes determining one or more global analysis parameters based on backtranslation of a first corpus between supported languages. A new text analysis model is determined for an unsupported language based on the one or more global analysis parameters and a text analysis model for a first supported language. An input text is analyzed in the unsupported language with the new text analysis model.

Abstract: A method for inferring a location where each textual message was posted by a test user method includes partitioning an area into a plurality of sub-areas, associating textual messages posted by training users with respective sub-areas where each textual message was posted, extracting a keyword characterizing each sub-area among one or more keywords obtained from each textual message posted by the training users associated with each sub-area, constructing a feature vector of the given sub-area based on each extracted keyword, computing a transition probability for the given sub-area by time-series of location information associated with the textual messages posted by the training user, computing a plurality of scores of each location, using the feature vector, where each textual message was posted by the test user, and computing, based on the plural scores and the transition probability, time-series of locations where each textual message was posted by the test user.

Abstract: A computer-implemented method, apparatus, and computer program product for evaluating a page in a website are provided. The method includes obtaining a link structure of the website. The method also includes identifying a page set, the page set being a set of pages linked to a specific page in the website. The method further includes calculating a degree of dispersion of the page set in the link structure. The method also includes evaluating the specific page using the degree of dispersion to generate a score for the specific page.

Abstract: A computer-implemented method, apparatus, and computer program product for evaluating a page in a website are provided. The method includes obtaining a link structure of the website. The method also includes identifying a page set, the page set being a set of pages linked to a specific page in the website. The method further includes calculating a degree of dispersion of the page set in the link structure. The method also includes evaluating the specific page using the degree of dispersion to generate a score for the specific page.

Abstract: Text analysis includes determining one or more global analysis parameters based on backtranslation of a first corpus between supported languages. A new text analysis model is determined for an unsupported language based on the one or more global analysis parameters and a text analysis model for a first supported language. An input text is analyzed in the unsupported language with the new text analysis model.

Abstract: A computer-implemented method for checking a search query used for retrieving information from a collection of records in an event sequence analysis system is disclosed. The method includes receiving a search query including a plurality of predicates and one or more constraints each associated with plural predicates, in which each predicate is specified to be positive or negative, and the plurality of the predicates forms a logical graph together with the one or more constraints. The method also includes generating from the graph a subgraph including one or more predicates specified to be positive among the plurality of the predicates. The method further includes determining whether the subgraph has plural components or not, and invalidating the search query in response to the subgraph being determined to have plural components.

Abstract: A system and computer implemented method for estimating difficulty of a document includes retrieving a subject document from a storage, setting difficulty of each keyword included in the subject document to locality of the keyword in the subject document as an initial value, estimating, by a processor, difficulty of each subject document by a statistical processing of the difficulties of keywords included in the subject document, and updating the difficulty of each keyword based on the difficulty of each subject document depending on a significance value of the keyword in the subject document.

Abstract: A system and method to estimate a location relating to a user who has not filled in information about the location in a profile field in social media such as a microblog. The system and method estimates association between a user in social media and a location includes the steps of acquiring a first content posted to the social media by a first user associated with a first location, determines regional localization of the first content on the basis of the first location, acquires a second content posted to the social media by a second user not associated with a location, determine the degree of a relationship between the first content and the second content, and associating the first location with the second user on the basis of the localization and the degree of the relationship.

Abstract: A computer-implemented method, apparatus, and computer program product for evaluating a page in a website are provided. The method includes obtaining a link structure of the website. The method also includes identifying a page set, the page set being a set of pages linked to a specific page in the website. The method further includes calculating a degree of dispersion of the page set in the link structure. The method also includes evaluating the specific page using the degree of dispersion to generate a score for the specific page.

Abstract: A computer-implemented method for checking a search query used for retrieving information from a collection of records in an event sequence analysis system is disclosed. The method includes receiving a search query including a plurality of predicates and one or more constraints each associated with plural predicates, in which each predicate is specified to be positive or negative, and the plurality of the predicates forms a logical graph together with the one or more constraints. The method also includes generating from the graph a subgraph including one or more predicates specified to be positive among the plurality of the predicates. The method further includes determining whether the subgraph has plural components or not, and invalidating the search query in response to the subgraph being determined to have plural components.

Abstract: A method, a computer system, and a computer program product for selecting electronic documents based on an expertness level for a target keyword. The method includes identifying a Lowest Common Ancestor (LCA) for each pair of categories to which documents in a document set belong based on a graph having edges which define relationships between nodes representing respective ones of the categories, the document set being associated with a target keyword, obtaining a degree of dispersion of the categories based on respective distances between the categories of each pair and the corresponding LCA, determining an expertness level for the target keyword based on the degree of dispersion, and in response to receiving a search query including the target keyword, selecting one or more documents from a database based on the expertness level for the target keyword.

Abstract: A method, a computer system, and a computer program product for determining an expertness level for a target keyword. The method includes preparing a document set associated with the target keyword, identifying, for each document in the document set, a category to which the document in the document set belongs, and determining an expertness level for the target keyword, based on a degree of dispersion of the identified categories. Each document in the document set may be associated with a category, and a graph which defines relations among the identified categories is generated from the identified categories to obtain the degree of dispersion of the identified categories. On condition that the degree of dispersion is lower, the expertness level for the target keyword may be determined to be higher or a higher expertness level is assigned to the target keyword.

Abstract: The present invention provides at least a method includes: extracting a plurality of partial communities from a plurality of users, based on the relationships of companion messages; computing a first degree of similarity for showing the similarity of the companion partial communities, based on the relationship of a user belonging to one partial community with a user belonging to the other partial community, from among the plurality of communities; computing a second degree of similarity for showing the similarity of companion partial communities, based on words within the messages sent by users belonging to both partial communities and under the condition that the first similarity be higher than a predetermined first threshold value; and creating an integrated community by integrating the companion partial communities under the condition that the second similarity be higher than a predetermined second threshold value.