A computer implemented method, system and a computer program product is provided for summarizing a document which includes receiving a reading speed of the reader, determining a summary length of a summary of the document based on the received reading speed of the reader, and generating a summary of the document having the determined summary length.

To detect information relating to the threat appropriately, based on an appearance tendency of information related to a threat in security. Information analysis system includes: an information storing unit that stores reference information acquired from an information source; and an information analysis unit that analyzes an appearance tendency of first phrase information that is included in the reference information acquired at chronologically different timings and that represents a phrase related to security and extracts reference information including the first phrase information the appearance tendency of which has changed from the information storing unit.

To detect information relating to the threat appropriately, based on an appearance tendency of information related to a threat in security. Information analysis system includes: an information storing unit that stores reference information acquired from an information source; and an information analysis unit that analyzes an appearance tendency of first phrase information that is included in the reference information acquired at chronologically different timings and that represents a phrase related to security and extracts reference information including the first phrase information the appearance tendency of which has changed from the information storing unit.

Embodiments of the application disclose a summary generation method and apparatus. A specific embodiment of the method comprises: acquiring a target article including a headline and a body of the article; determining whether a question is included in the headline; determining, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline; and generating a summary of the target article based on the determined information-satisfied-paragraph. The above embodiment may generate a summary that directly satisfies the users' demand for information.

Embodiments of the application disclose a summary generation method and apparatus. A specific embodiment of the method comprises: acquiring a target article including a headline and a body of the article; determining whether a question is included in the headline; determining, in the body of the article, an information-satisfied-paragraph including an answer to the question, in response to determining that the question is included in the headline; and generating a summary of the target article based on the determined information-satisfied-paragraph. The above embodiment may generate a summary that directly satisfies the users' demand for information.

Disclosed is a computer method of facilitating drafting of legislation. The method includes receiving a subject indicator from a legislator device. Further, the method includes analyzing the subject indicator. Further, the method includes retrieving a plurality of suggested legal constructs from a storage device based on the analyzing of the subject indicator. Further, the method includes transmitting the plurality of suggested legal constructs to the legislator device. Moreover, the method includes receiving a plurality of selected legal constructs from the legislator device. Further, the method includes analyzing the plurality of selected legal constructs based on a plurality of rules. Further, the method includes generating at least one suggested legislation based on the analyzing of the plurality of selected legal constructs. Further, the method includes storing the at least one suggested legislation in the storage device. Moreover, the method includes transmitting the at least one suggested legislation to the legislator device.

Systems and methods are provided for generating classification data which is used for classifying documents. The method includes reading documents in a form of a spreadsheet; collecting cell values in each of the documents; finding one or more common cell values among the collected values; counting, for each of the common cell values, a number of the documents having the common cell value; storing, if the number of the documents is equal to or larger than a predetermined number, the common cell value as a candidate header label in a memory; calculating a distance between cell locations of the candidate header labels in each of the documents; choosing, according to the calculated distance, two or more candidate header labels among the candidate header labels for each of the documents; and storing one or more combinations of the chosen two or more candidate header labels as the classification data.

Generating a table of contents from a computer document is disclosed. The computer document is converted into a markup language, from which a list of grouped textblocks is generated. Headings are detected from among the list of grouped textblocks. For a grouped textblock, a first vector corresponding to a semantic representation of the grouped textblock and a second vector based on evaluation of pre-defined features in the grouped textblock are generated. Based on the first and second vectors, the grouped textblock is classified as a heading or a plain-text using a trained classifier.

Generating a table of contents from a computer document is disclosed. The computer document is converted into a markup language, from which a list of grouped textblocks is generated. Headings are detected from among the list of grouped textblocks. For a grouped textblock, a first vector corresponding to a semantic representation of the grouped textblock and a second vector based on evaluation of pre-defined features in the grouped textblock are generated. Based on the first and second vectors, the grouped textblock is classified as a heading or a plain-text using a trained classifier.

Sentences associated with diagrams or tables are extracted in a wider range. In a sentence extracting device that includes a processor and extracts a sentence associated with a diagram or a table from a body of a digital document including the diagram or the table and the body, the diagram or the table includes a label, a caption, and a body. The processor includes extraction units 202 to 205 that extract, from the body, a sentence including a second word associated with a first word included in the body of the diagram or the table.