Abstract: An information processing system comprises a processor for executing a program, a storage device for storing the program, a word dictionary database for storing a word group corresponding to a group of words grouped according to a predetermined attribute and a rule database for storing a tree structure pattern obtained by abstracting tree structure data indicating relations between words in a sentence, by use of the word group. The processor executes acceptance processing of accepting a maintenance request, and maintenance processing of, when the maintenance request accepted in the acceptance processing is a maintenance request related to a word, maintaining the word dictionary database as for a word group, the word belonging to the word group, while when the maintenance request is a maintenance request related to the tree structure pattern, maintaining the rule database as for the tree structure pattern.

Abstract: A text classification device includes an important word extraction portion that extracts important words from analysis target text data, a distributed representation creation portion that creates distributed representations of words from related document data, a keyword candidate creation portion that extracts words near the important words as synonyms in the distributed representations of the words, a clustering portion that clusters the distributed representations of the important words and synonyms and creates a term cluster, and a viewpoint word creation portion that extracts a hypernym that is a word having a generalized concept of a term in the term cluster using a knowledge base in which relationships between terms are accumulated and creates a viewpoint dictionary in which a viewpoint word selected from the hypernyms is set as a headword and the terms included in the term cluster are set as keywords for the headword.

Abstract: To attempt to enhance the scenario creation efficiency. A creation assisting device can access a database storing a set of relational knowledge data including two nodes defining knowledge, and an edge defining a relationship between the nodes, and linking the nodes, acquires an inference route defining an order of pieces of knowledge forming a hypothesis, updates a scenario embodying the hypothesis if a second node corresponding to a first node in an inference route is added to the scenario, generates a first search query for searching for a second destination node from the second node, on a basis of the first node in the inference route, a first destination node from the first node, and a first edge linking the first node, and the first destination node, searches the database for particular first relational knowledge data corresponding to the first search query, and outputs the particular first relational knowledge data.

Abstract: A data acquisition device is accessible to correspondence information that defines correspondence between an attribute keyword indicating an attribute and a non-attribute keyword that does not indicate the attribute, and is configured to execute: specifying the attribute keyword corresponding to the non-attribute keyword when the search keyword is the non-attribute keyword with respect to each of a plurality of search keywords; assigning the search keyword to a character string in a retrieval target document corresponding to the search keyword; extracting a specific table assigned with the annotation from one or more tables; selecting at least one of a specific row and a specific column relevant to each of the plurality of search keywords from rows and columns that constitute the specific table extracted on the basis of the annotation; and acquiring a cell in the specific table specified by a first selection result.

Abstract: A data processing system executes data processing by accessing a database. The database has a data structure including extraction target data of natural language from a data source and a search target data that is associated with the extraction target data and that can be interpreted in the data processing, and the search target data includes first attribute information of natural language indicating attribute of the extraction target data and annotation information by associating a noun phrase of natural language indicating annotation related to the extraction target data and second attribute information of natural language indicating an attribute of the annotation, the first attribute information is information searched with a first search character string specific to the data processing when an input character string is given, and the annotation information is information searched based on the input character string to the data processing when the input character string is given.

Abstract: A data acquisition device is accessible to correspondence information that defines correspondence between an attribute keyword indicating an attribute and a non-attribute keyword that does not indicate the attribute, and is configured to execute: specifying the attribute keyword corresponding to the non-attribute keyword when the search keyword is the non-attribute keyword with respect to each of a plurality of search keywords; assigning the search keyword to a character string in a retrieval target document corresponding to the search keyword; extracting a specific table assigned with the annotation from one or more tables; selecting at least one of a specific row and a specific column relevant to each of the plurality of search keywords from rows and columns that constitute the specific table extracted on the basis of the annotation; and acquiring a cell in the specific table specified by a first selection result.

Abstract: A sentence creation system, which outputs an opinion sentence on an agenda, includes: an input unit into which the agenda is input; an agenda analyzing unit analyzing the agenda and judging the polarity of the agenda and a keyword used for searching; a searching unit searching for articles using the keyword and a disputed point word showing a disputed point in the discussion; a disputed point determining unit for determining the disputed point used for creating the opinion sentence; a sentence extracting unit for extracting sentences in which the disputed point is described among the articles output by the searching unit; a sentence sorting unit for creating sentences by sorting the extracted sentences; an evaluating unit for evaluating the sentences; a paraphrasing unit for inserting appropriate conjunctions into the sentences; and an output unit for outputting the most highly evaluated sentence among the plural sentences as the opinion sentence.

Abstract: An information processing system comprises a processor for executing a program, a storage device for storing the program, a word dictionary database for storing a word group corresponding to a group of words grouped according to a predetermined attribute and a rule database for storing a tree structure pattern obtained by abstracting tree structure data indicating relations between words in a sentence, by use of the word group. The processor executes acceptance processing of accepting a maintenance request, and maintenance processing of, when the maintenance request accepted in the acceptance processing is a maintenance request related to a word, maintaining the word dictionary database as for a word group, the word belonging to the word group, while when the maintenance request is a maintenance request related to the tree structure pattern, maintaining the rule database as for the tree structure pattern.

Abstract: A data processing system executes data processing by accessing a database. The database has a data structure including extraction target data of natural language from a data source and a search target data that is associated with the extraction target data and that can be interpreted in the data processing, and the search target data includes first attribute information of natural language indicating attribute of the extraction target data and annotation information by associating a noun phrase of natural language indicating annotation related to the extraction target data and second attribute information of natural language indicating an attribute of the annotation, the first attribute information is information searched with a first search character string specific to the data processing when an input character string is given, and the annotation information is information searched based on the input character string to the data processing when the input character string is given.

Abstract: Information appropriate for supporting various judgments in organization activities is provided. A judgment support system for supporting a user's judgment, includes: a processor that executes a program; a storage section that can be accessed by the processor; and an output section that outputs data for displaying an execution result of the program. The judgment support system further includes: an extraction section that searches a predetermined sentence expression from data stored in the storage section, and extracts an issue of an organization using text having a predetermined relationship with the searched sentence expression; and a first selection section that selects a second organization confronted with an issue similar to an issue of a first organization to be analyzed, and that selects measures against the issue of the second organization from the data stored in the storage section. The output section outputs data for displaying the selected issue and the selected measures.

Abstract: A sentence creation system, which outputs an opinion sentence on an agenda, includes: an input unit into which the agenda is input; an agenda analyzing unit analyzing the agenda and judging the polarity of the agenda and a keyword used for searching; a searching unit searching for articles using the keyword and a disputed point word showing a disputed point in the discussion; a disputed point determining unit for determining the disputed point used for creating the opinion sentence; a sentence extracting unit for extracting sentences in which the disputed point is described among the articles output by the searching unit; a sentence sorting unit for creating sentences by sorting the extracted sentences; an evaluating unit for evaluating the sentences; a paraphrasing unit for inserting appropriate conjunctions into the sentences; and an output unit for outputting the most highly evaluated sentence among the plural sentences as the opinion sentence.