Sharp Kabushiki Kaisha Corporation

Takeshi Kutsumi

Ichiko Sata

Yoji Fukumochi

Tokuyuki Hirai

Shuzo Kugimiya

Hitoshi Suzuki

Toshiyuki Okunishi

Kazuo Nishiura

Naoko Shinozaki

Ai Fujiwara

Chinami Hino

A document generating apparatus and a document generating method capable of easily and effectively generating a document with a supplementary explanation in which a supplementary explanation character string is given in a ruby form in a character size which conforms to a character size of a document. The document generating apparatus (and method thereof) decides, for each line, a character size for characters included in each line in each character area, and corrects information on the character size based on the calculated value of the character size.

Correcting a document character size based on the average value of each character size

Regarding a wording including a character stored neither in character DBstoring characters whose shapes have portions to be positioned under a base line nor in other character DBstoring characters that are positioned to separate upward from the base line, a mean YBav calculated with bottom Y coordinates of all characters neither stored in the DBnor DBis designated as a bottom Y coordinate of wording. Regarding a wording including only characters stored in the DB, a predetermined value is added to a mean YBavcalculated with bottom Y coordinates of all characters for obtaining an YBav designated as a bottom Y coordinate of wording. Regarding a wording configured with only characters stored in the DB, a predetermined value is subtracted from a mean YTav calculated with top Y coordinates of all character marks for obtaining a YBav designated as a bottom Y coordinate of wording.

Document image generating apparatus, document image generating method and computer program, with adjustment of ruby-added image

An expression, for which complementary information can be outputted, is extracted from a document obtained by character recognition for an image. Complementary information related to the extracted expression is outputted when a character or a symbol adjacent to the beginning or the end of the extracted expression is not a predetermined character or symbol. Output of complementary information related to the extracted expression is skipped when the character or symbol adjacent to the beginning or the end of the extracted expression is the predetermined character or symbol. A problem that complementary information unrelated to an original text is outputted is prevented even when a false character recognition occurs.

Information output device and information output method

The object of this invention is to provide an image processing apparatus in which, in processing of a document image read by a document reading device, an inclination of a character string in the document image which is recognized in character recognition is obtained more accurately. The image processing apparatus includes a similar character extraction portion which extracts and outputs a character group comprised of characters having a shape and a size that are same with or similar to each other from among characters constituting a character string comprised of a character recognized in optical character recognition from a document image read by a document reading device; and an inclination calculation portion which calculates an inclination value of the character string based on position information of each character of the character group output from the similar character extraction portion.

Image processing apparatus

A ruby character is displayed in an appropriate display form corresponding to characteristics of a layout of a document intended for giving of ruby characters. In a document generating apparatus, a storage portion stores information on a layout of a document as document layout data, a unification judging portion reads the document layout data stored in the storage portion, and a ruby character setting portion judges unification of a layout of the whole document based on the read document layout data to set a display form of a ruby character based on a judgment result by the unification judging portion.

Document generating apparatus, document generating method, computer program and recording medium

A character is recognized from an original document image that is obtained, for example, by an image reading apparatus. And a natural language processing is performed on a document configured from the recognized characters. Thus, a translation (supplementary annotation) for a word or a phrase in the document is obtained. Then, a supplementary annotation added document image is generated with an original document image layer configured from an original document image on which a supplementary annotation text layer is superimposed. In the supplementary annotation text layer, the translation is placed at a position corresponding to a position in an interline space near the word or the phrase. Furthermore, in addition to a translation, an underline is placed for a discontinuous phrase.

Document image generation apparatus, document image generation method and recording medium

It is expected to provide a document image generating apparatus, a document image generating method and a computer program that can keep a layout of original text present in the original text image and then can improve the readability of original text and the readability annotation corresponding to the original text (e.g., translation). A translationof original textis aligned at the interline space between the original textat the first line and the original textat the second line. When the interline space is narrow as shown in FIG.B, the original textoverlays the translation. At that time, the color regarding the original textis changed to be a low visibility color, and the color regarding the translationis changed to be a high visibility color.

Document image generating apparatus, document image generating method and computer program

A learning support system has an information processing apparatus, a portable information terminal and a learning management server which are connected through a network. The information processing apparatus includes a second memory unit for storing first learning information which includes result of learning, and the portable information terminal includes a fourth memory unit for storing second learning information which includes result of learning at the portable information terminal, and the learning management server includes a fifth memory unit for storing the first learning information transferred from the information processing apparatus and the second learning information transferred from the portable information terminal. The information processing apparatus or the portable information terminal carries out continuous learning after learning information of other party is acquired through the fifth memory unit.

Learning support system

A translator includes a word dictionary, an affix dictionary, an input section for inputting an original language to be a first language, a converting section for referring to the word dictionary, thereby converting the input original language into a translated word to be a second language, a recognizing section for referring to the word dictionary and the affix dictionary, thereby recognizing a derivative having an affix and a word base from the input original language which cannot be converted into the translated word by the converting section, a derivative translation generating section for linking a translated word corresponding to the affix of the recognized derivative to a translated word corresponding to the word base, thereby generating a translated word of one derivative, and an affix determining section for determining one affix based on an affix processing condition given from a language characteristic information when a derivative including a plurality of affixes is recognized by the recognizing section, wherein the derivative translation generating section generates a translated word of a derivative having the affix determined by the affix determining section and a word base corresponding thereto.

Translator, translating method and recording medium having translating program recorded thereon

A translation machine is arranged to derive two or more syntaxes from one original sentence, determine which of the syntaxes is the most approximate according to a syntax priority rule given by a user or a manufacturer and output a translated sentence based on the most approximate syntax. The translation machine includes a memory, a translating module and a main CPU as main components. The memory serves to store a partial structure of each syntax and a syntax priority rule containing a numerical value indicating a priority of the partial structure and an incidental condition of the syntax. The translating module serves to collide the syntax priority rule stored in the memory with the syntax of the original sentence and giving a proper evaluating value to the syntax of the original sentence. The main CPU serves to output the translated sentences on the syntaxes derived from the original sentence according to their larger evaluating values.

Translation machine having a function of deriving two or more syntaxes

A machine translation apparatus for translating a source language sentence into a target language sentence according to the present invention includes: an analysis unit for analyzing the source language sentence and generating a syntax tree of the source language; a conversion unit for converting the syntax tree of the source language into a syntax tree of the target language; and a generation unit for generating the target language sentence based on the syntax tree of the target language. The machine translation apparatus further includes: a correspondence information storage unit for storing information of correspondence between words in the source language sentence and words in the target language sentence obtained by the generation unit; a positioning unit for determining division positions at which to divide the source language sentence into phrases in the source language based on phrase categories in the syntax tree of the source language generated by the analysis unit; a translated phrase building unit for dividing the source language sentence at the division positions and generating phrases in the target language corresponding to the phrases in the source language; an output formatting unit for generating an output format for displaying the phrases in the source language so that the phrases in the source language correspond to the phrases in the target language; and a display unit for outputting the phrases in the source language and the phrases in the target language onto a display screen.

Machine translation apparatus

A machine translation system having an idiom processing function is disclosed, which includes a keyboard for inputting a word sequence of a first language; a dictionary memory for storing therein idioms of the first language including at least two fixed portions and a variable portion interposed therebetween as headers and translated expressions in a second language corresponding to the respective headers; and a control processor for performing a registration process for newly or additionally registering a header of the first language and translated expressions in the second language corresponding to the header into the dictionary memory, a dictionary lookup process for retrieving a header corresponding to an idiom included in the word sequence of the first language input by means of the keyboard from the headers stored in the dictionary memory by comparing the word sequence of the first language with each of the headers, and an idiom processing process for normalizing an arrangement of fixed portions in a word sequence of the first language which is identified with one of the headers in the dictionary lookup process.

Machine translation system having idiom processing function

In a machine translation system, a default translation flag for indicating a default equivalent word is set in a dictionary in a memory. A normal equivalent-word selector of a translation module executes semantic analysis on a case structure tree determined by a dictionary-lookup morpheme analyzing part, a syntax analyzer, and a tree structure transforming unit. If the case structure tree has failed in the semantic analysis, a special equivalent-word selector executes a default translation processing to adopt the default equivalent word indicated by the default translation as an optimum equivalent word such that the case structure tree is passed. Thus, even if the case structure tree has failed in the semantic analysis due to strict semantic restrictions, a translation can be securely generated. Further, if the case structure tree has not failed in the semantic analysis, a high-accuracy translation can be generated.

Machine translation system generating a default translation

An apparatus for aiding adding to a dictionary words which take various forms such as irregular verbs, phrasal expressions, etc. includes: a unit for obtaining the original form of a target word which a user desires to add to the dictionary; a unit for receiving variants of the target word input by the user from a prescribed input region; a manually operable input unit for editing, at a cursor position, a character string displayed on the input region; a unit for displaying the original form on the input region and positioning the cursor at a character location with the highest possibility that the original form and a variant form are different, prior to receiving the variant; and a unit for storing the original form and the variant in association with each other into a user dictionary. A language processing apparatus including such an apparatus for aiding adding to a dictionary is also disclosed. When the user inputs the original form of a word to the apparatus, the original form is displayed on the input region prior to inputting its variant form. The cursor is positioned at the character location of the original form which has the highest possibility of being different from the variant form. Thus the labor of adding various forms of the same word into the dictionary is reduced.

Growing community of inventors

Osaka, Japan

Takeshi Kutsumi