Foreign language sentence creation support apparatus, method, and program

• US 10,394,961 B2
• Filed: 10/30/2015
• Issued: 08/27/2019
• Est. Priority Date: 11/04/2014
• Status: Expired due to Fees

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation), Toshiba Solutions Corporation (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Zu, Guowei, Kano, Toshiyuki
• Primary Examiner(s): Sirjani, Fariba
• Application Number:
  US14/927,720
• Publication Number:
  US 20160124943A1
• Time in Patent Office: 1,397 Days
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory

Abstract

According to one embodiment, an input unit accepts input of an input sentence that is a second sentence of the native language corresponding to a first sentence. A language analysis execution unit executes language analysis for the input sentence. A grammatical feature extraction unit extracts a grammatical feature of the input sentence based on a result of the executed language analysis. A search query generation unit generates a search query based on the extracted grammatical feature. An output unit searches for an index based on the generated search query and outputs an exemplary sentence set including an exemplary sentence of the native language corresponding to an index that matches the search query and an exemplary sentence of the foreign language corresponding to the exemplary sentence of the native language.

Claims

1. A foreign language sentence creation apparatus for creation of a first sentence of a foreign language, which is a sentence formed from a plurality of clauses including at least an independent word, comprising:

a computer memory configured to store an exemplary sentence corpus that includes an exemplary sentence collection including an exemplary sentence set including an exemplary sentence of the foreign language and an exemplary sentence of a native language corresponding to the exemplary sentence of the foreign language, and an index corresponding to the exemplary sentence of the native language; and

a processor, in communication with the computer memory, that executes the operations of;

an input circuit configured to accept input of an input sentence that is a second sentence of the native language corresponding to the first sentence;

a language analysis execution circuit configured to execute language analysis including morphological analysis and syntax analysis for the input sentence whose input has been accepted;

a grammatical feature extraction circuit configured to extract a grammatical feature of the input sentence based on a result of the executed language analysis, the grammatical feature including information of a main verb, a sentence pattern, a function word, and a sentence composition;

a search query generation circuit configured to generate a search query including the extracted grammatical feature; and

a search circuit configured to automatically search for the index based on the generated search query, wherein the search is a search of the computer memory; and

a display configured to display a plurality of exemplary sentence sets, each of the plurality of exemplary sentence sets including an exemplary sentence of the native language corresponding to an index that matches the search query and an exemplary sentence of the foreign language corresponding to the exemplary sentence of the native language,

wherein a grammatical feature of each of the plurality of exemplary sentence set is similar to the grammatical feature of the input sentence, and the plurality of exemplary sentence sets include an exemplary sentence set having information different from information of the input sentence; and

wherein the search query generation circuit is further configured to extend the search query by applying postpositional particle extension to the search query.

2. The apparatus of claim 1, wherein the search query generation circuit is further configured to extend the search query by applying at least one of indeclinable word abstraction, synonym extension, and intransitive/transitive verb extension to the search query.

3. The apparatus of claim 1, wherein the grammatical feature extraction circuit further comprises:

a semantic attribute analysis circuit which executes semantic attribute analysis of the input sentence based on the result of the executed language analysis; and

an extraction circuit which extracts the grammatical feature of the input sentence based on a result of the executed semantic attribute analysis.

4. The apparatus of claim 3, wherein the result of the semantic attribute analysis includes a semantic attribute of an independent word in the input sentence on a hierarchical level basis,

the extraction circuit extracts the grammatical feature including the semantic attribute on the hierarchical level basis, and

the search query generation circuit generates the search query by selecting the hierarchical level of the semantic attribute to be applied to the search query.

5. A foreign language sentence creation apparatus for creation of a first sentence of a foreign language, which is a sentence formed from a plurality of clauses including at least an independent word, comprising:

a computer memory configured to store an exemplary sentence corpus that includes an exemplary sentence collection including an exemplary sentence of the foreign language and an index corresponding to the exemplary sentence of the foreign language; and

a processor, in communication with the computer memory, that executes the operations of;

an input circuit configured to accept input of an input sentence that is an evaluation target sentence of the foreign language;

a language analysis execution circuit configured to execute language analysis including morphological analysis for the input sentence whose input has been accepted;

a grammatical feature extraction circuit configured to extract a grammatical feature of the input sentence based on a result of the executed language analysis, the grammatical feature including information of a main verb, a sentence pattern, a function word, and a sentence composition;

a search query generation circuit configured to generate a search query based on the extracted grammatical feature; and

a search circuit configured to automatically search a storage medium for the index based on the generated search query; and

a display configured to display a plurality of exemplary sentences, each of the plurality of exemplary sentences being an exemplary sentence of the foreign language corresponding to an index that matches the search query,

wherein a grammatical feature of each of the plurality of exemplary sentences is similar to the grammatical feature of the input sentence, and the plurality of exemplary sentences include an exemplary sentence set having information meaning different from information of the input sentence; and

wherein the search query generation circuit is further configured to extend the search query by applying postpositional particle extension to the search query.

6. The apparatus of claim 5, wherein the memory stores the exemplary sentence corpus including an exemplary sentence collection that further includes an exemplary sentence of a native language corresponding to the exemplary sentence of the foreign language, and

the output circuit further outputs the exemplary sentence of the native language corresponding to the exemplary sentence of the foreign language corresponding to the index that matches the search query.

7. The apparatus of claim 5, wherein search query generation circuit is further configured to extend the search query by applying at least one of indeclinable word abstraction, synonym extension, and intransitive/transitive verb extension to the search query.

8. The apparatus of claim 5, wherein the grammatical feature extraction circuit further comprises:

a semantic attribute analysis circuit which executes semantic attribute analysis of the input sentence based on the result of the executed language analysis; and

an extraction circuit which extracts the grammatical feature of the input sentence based on a result of the executed semantic attribute analysis.

9. The apparatus of claim 8, wherein the result of the semantic attribute analysis includes a semantic attribute of an independent word in the input sentence on a hierarchical level basis,

the extraction circuit extracts the grammatical feature including the semantic attribute on the hierarchical level basis, and

the search query generation circuit generates the search query by selecting the hierarchical level of the semantic attribute to be applied to the search query.

10. A foreign language sentence creation method for creation of a first sentence of a foreign language, which is a sentence formed from a plurality of clauses including at least an independent word, comprising:

storing, by a foreign language sentence creation apparatus comprising a processor, an exemplary sentence corpus that includes an exemplary sentence collection including an exemplary sentence set including an exemplary sentence of the foreign language and an exemplary sentence of a native language corresponding to the exemplary sentence of the foreign language, and an index corresponding to the exemplary sentence of the native language;

accepting, by the apparatus, input of an input sentence that is a second sentence of the native language corresponding to the first sentence;

executing, by the apparatus, language analysis including morphological analysis and syntax analysis for the input sentence whose input has been accepted;

extracting, by the apparatus, a grammatical feature of the input sentence based on a result of the executed language analysis, the grammatical feature including information of a main verb, a sentence pattern, a function word, and a sentence composition;

generating, by the apparatus, a search query including the extracted grammatical feature;

automatically searching, by the apparatus, the internet for the index based on the generated search query; and

outputting, by the apparatus and on a display, to a user a plurality of exemplary sentence sets, each of the plurality of exemplary sentence sets including an exemplary sentence of the native language corresponding to an index that matches the search query and an exemplary sentence of the foreign language corresponding to the exemplary sentence of the native language,

wherein a grammatical feature of each of the plurality of exemplary sentence sets is similar to the grammatical feature of the input sentence, and the plurality of exemplary sentence sets include an exemplary sentence set having information different from information of the input sentence, and

wherein the searching for the index comprises extending the search query by applying postpositional particle extension to the search query.

11. A foreign language sentence creation method for creation of a first sentence of a foreign language, which is a sentence formed from a plurality of clauses including at least an independent word, comprising:

storing, by a foreign language sentence creation apparatus comprising a processor, an exemplary sentence corpus that includes an exemplary sentence collection including an exemplary sentence of the foreign language and an index corresponding to the exemplary sentence of the foreign language;

accepting, by the apparatus, input of an input sentence that is an evaluation target sentence of the foreign language;

executing, by the apparatus, language analysis including morphological analysis for the input sentence whose input has been accepted;

extracting, by the apparatus, a grammatical feature of the input sentence based on a result of the executed language analysis, the grammatical feature including information of a main verb, a sentence pattern, a function word, and a sentence composition;

generating, by the apparatus, a search query including the extracted grammatical feature;

searching, by the apparatus, for the index automatically based on the generated search query, wherein the search is a search of a storage medium that accesses the internet; and

outputting, by the apparatus and on a display, a plurality of exemplary sentences, each of the plurality of exemplary sentences being an exemplary sentence of the foreign language corresponding to an index that matches the search query,

wherein a grammatical feature of each of the plurality of exemplary sentences is similar to the grammatical feature of the input sentence, and the plurality of exemplary sentences include an exemplary sentence having information different from information of the input sentence; and

wherein the searching for the index comprises extending the search query by applying postpositional particle extension to the search query.

12. A non transitory computer readable storage medium that stores a program which is executed by a foreign language sentence creation apparatus for creation of a first sentence of a foreign language, which is a sentence formed from a plurality of clauses including at least an independent word, the program comprising:

a first program code, executable by a processor of the apparatus, which causes the foreign language sentence creation support apparatus to store an exemplary sentence corpus that includes an exemplary sentence collection including an exemplary sentence set including an exemplary sentence of the foreign language and an exemplary sentence of a native language corresponding to the exemplary sentence of the foreign language, and an index corresponding to the exemplary sentence of the native language;

a second program code, executable by the processor, which causes the foreign language sentence creation support apparatus to accept input of an input sentence that is a second sentence of the native language corresponding to the first sentence;

a third program code, executable by the processor, which causes the foreign language sentence creation support apparatus to execute language analysis including morphological analysis and syntax analysis for the input sentence whose input has been accepted;

a fourth program code, executable by the processor, which causes the foreign language sentence creation support apparatus to extract a grammatical feature of the input sentence based on a result of the executed language analysis, the grammatical feature including information of a main verb, a sentence pattern, a function word, and a sentence composition;

a fifth program code, executable by the processor, which causes the foreign language sentence creation support apparatus to generate a search query including the extracted grammatical feature;

a sixth program code, executable by the processor, which causes the foreign language sentence creation support apparatus to automatically search a storage unit for the index based on the generated search query; and

a seventh program code, executable by the processor, which outputs via a display device a plurality of exemplary sentence sets, each of the plurality of exemplary sentence sets including an exemplary sentence of the native language corresponding to an index that matches the search query and an exemplary sentence of the foreign language corresponding to the exemplary sentence of the native language,

wherein a grammatical feature of each of the plurality of exemplary sentence sets is similar to the grammatical feature of the input sentence, and the plurality of exemplary sentence sets include an exemplary sentence set having information different from information of the input sentence; and

wherein the fifth program code extends the search query by applying postpositional particle extension to the search query.

13. A non transitory computer readable storage medium that stores a program which is executed by a foreign language sentence creation apparatus for creation of a first sentence of a foreign language, which is a sentence formed from a plurality of clauses including at least an independent word, the program comprising:

a first program code, executable by a processor of the apparatus, which causes the foreign language sentence creation support apparatus to store an exemplary sentence corpus that includes an exemplary sentence collection including an exemplary sentence of the foreign language and an index corresponding to the exemplary sentence of the foreign language;

a second program code, executable by the processor, which causes the foreign language sentence creation support apparatus to accept input of an input sentence that is an evaluation target sentence of the foreign language;

a third program code, executable by the processor, which causes the foreign language sentence creation support apparatus to execute language analysis including morphological analysis for the input sentence whose input has been accepted;

a fourth program code, executable by the processor, which causes the foreign language sentence creation support apparatus to extract a grammatical feature of the input sentence based on a result of the executed language analysis, the grammatical feature including information of a main verb, a sentence pattern, a function word, and a sentence composition;

a fifth program code, executable by the processor, which causes the foreign language sentence creation support apparatus to generate a search query including the extracted grammatical feature;

a sixth program code, executable by the processor, which causes the foreign language sentence creation support apparatus to search automatically for the index based on the generated search query, wherein the search is a search of a storage media that accesses the internet; and

a seventh program code, executable by the processor, which outputs on a display device a plurality of exemplary sentences, each of the plurality of exemplary sentences being an exemplary sentence of the foreign language corresponding to an index that matches the search query,

wherein a grammatical feature of each of the plurality of exemplary sentences is similar to the grammatical feature of the input sentence, and the plurality of exemplary sentences include an exemplary sentence having information different from information of the input sentence; and

wherein the fifth program code extends the search query by applying postpositional particle extension to the search query.