摘要:
An information filtering apparatus for providing articles to a user includes an article extraction section that retrieves articles from articles stored in an article storage section using a user-profile. An excerpt generating section generates excerpts of the retrieved article by calculating similarities between the retrieved articles and the user-profile to generate the excerpt including the user's necessary information. An abstract generating section combines excerpts to form an abstract. The user-profile for each user in the user-profile storage section is modified in accordance with user feedback.
摘要:
An information filtering apparatus for receiving articles, such as texts or images, from information sources to select predetermined articles from the supplied articles to a user has a storage portion, an article retrieving portion, a determining portion and a presentation portion. The storage portion stores retrieving conditions previously specified for each user. The article retrieving portion retrieves the supplied articles to select articles which satisfy the retrieving conditions for each user. The determining portion calculates similarities among the articles selected by the article retrieving portion or the selected articles and other articles to determine relevant articles for each article in accordance with the similarities. The presentation portion adds information of the determined relevant articles to the selected articles to present the articles and information to the user.
摘要:
The present invention is a device and method for filtering information, the device comprising a document database storing document data to be filtered, a reproduced document information storing unit storing fundamental document data used for detection of documents, newly created or updated, a detecting unit for detecting a document, newly created or updated, among document data stored in the document database based on document data stored in the document database and the fundamental document data stored in the reproduced document information storing unit, a similarity computing unit for computing a similarity between the detected document detected by the detecting unit and a retrieval condition set in advance, and a presenting unit for presenting detected documents detected by the detecting unit according to the similarities computed by the similarity computing unit.
摘要:
A document retrieval system is provided with an original sentence processing unit which sets a plurality of sentence types for identifying the contents of sentences, such as "OPINION" and "PROPOSAL," prepares sentence-unit excerpt sentence data classified according to the sentence types from an original sentence database storing original sentence data constituting documents, and stores the excerpt sentence data as excerpt sentence database. The original sentence processing unit comprises a type determination section for extracting excerpt sentence data corresponding to a designated sentence type, and a shaping section for shaping the excerpt sentence data in a predetermined format, e.g., in such a format that a conjunctive is deleted.
摘要:
A document detection system capable of detecting a desired document from a large number of documents easily and accurately in which the user can make a judgement concerning the appropriateness of the detection result quickly. In the system, those documents which contain a semantic structure of a detection command containing natural language expressions entered by a user are detected. Also, the keywords of each document can be extracted from the summary of each document and those documents whose keywords match with detection keywords specified by a user can be detected. Also, the summary of each detected document can be automatically generated according to text structures of each detected document and displayed along with the detected document itself. Also, the detection processing can be carried out with respect to the summaries of the documents instead of the documents themselves.
摘要:
A document detection system using a detection result presentation that can facilitate a user's quick comprehension of the relevancy of each detected document. In this system, a user's input for commanding a document detection is analyzed to extract keywords and viewpoints relevant to each keyword contained in the user's input, and a detection command is constructed from the keywords and the viewpoints extracted from the user's input. Then, the detection operation is executed to detect those documents among a plurality of stored documents which match with the constructed detection command as detected documents for a detection result. The detection result can be presented in the multi-dimensional display formed by setting the viewpoints to axes with the detection command as an origin and using distances of the detected documents with respect to the origin for each viewpoint as coordinates of the detected documents with respect to each axis representing each viewpoint.
摘要:
A machine translation system has a display section, an original storage section for storing an original sentence, a dictionary storing linguistical information necessary for translation processing, a translation processing section for translating the original sentence for each predetermined processing unit to obtain a translated sentence, a translation storage section for storing the translated sentence, an edit processing section for executing edit processing for the original and translated sentences, and an input section for inputting instruction information. In addition, the system has a display control section for realizing a first display mode for displaying the original and translated sentences respectively on original and translation display sections of a display screen of the display section, a second display mode for mainly displaying the original sentences on the display screen, and a third display mode for mainly displaying the translated sentences on the display screen. The display control section selectively switches the three display modes in response to information for instructing a display mode switching operation.
摘要:
A language expression data base is adapted to store expression data of an input sentence of a first language to be translated into a second language and the expression data stored in the language expression data base is renewed under the control of an expression data input unit. An input basic form sentence structure data extracted from the input sentence of the first language is translated into a basic form sentence structure data of the second language at the sentence structure transfer unit. A basic form sentence of the second language is obtained on the basis of the basic form sentence structure data of which an expression is then modified according to the expression data stored in the language expression data base, and a modified sentence of the second language is displayed on a display through an output unit.
摘要:
A machine translation system is capable of automatically and correctly analyzing a sentence having an inserted comment of a first language by means of a specific dictionary. The dictionary includes a first dictionary in accordance with which the inserted comment is extracted and analyzed and a second dictionary in accordance with which the other portion of the sentence than the inserted comments is analyzed. An analysis of the inserted comment and an analysis of the other portion are combined to obtain an analysis of the overall sentence. The translated sentence in the second language is produced in accordance with the analysis of the sentences which is combined. Furthermore, the translated inserted comment is displayed in a distinguishable manner. Specifically, a symbol for showing the inserted comment is added to the translated inserted comment. The translated sentence is displayed for including the inserted comment with the symbol.
摘要:
A machine translation system has an input unit for inputting an original sentence, a dictionary section for storing language information used in translation processing, a translation processor for translation-processing the original sentence with reference to the language information stored in the dictionary section, and an output unit for outputting a translated sentence obtained by the translation processor. The translation processor has an analysis section, a translated sentence generation section, and a punctuation mark generation section. The analysis section analyzes the original sentence. The translated sentence generation section generates the translated sentence in accordance with the analysis result of the analysis section. The punctuation mark generation section generates a punctuation mark substantially independently of a punctuation mark present in the original sentence, and appropriately inserts it in the translated sentence.