APPARATUS AND METHOD FOR PROCESSING TEXT

• US 20160253318A1
• Filed: 02/29/2016
• Published: 09/01/2016
• Est. Priority Date: 02/27/2015
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: LEE, Jimin, KIM, Kyungtae, KANG, Sangki
• Application Number:
  US15/055,748
• Publication Number:
  US 20160253318A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06F 40/279 Recognition of textual entities
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation

Abstract

An apparatus and a method of processing text are disclosed. The method includes: summarizing the text by extracting at least one sentence from the text; identifying attributes of analysis units included in the sentence of the summarized text; and translating the summarized text based on the identified attributes.

Claims

1. A method of processing text, the method comprising:

summarizing text by extracting at least one sentence from the text;

identifying attributes of analysis units included in the sentence of the summarized text; and

translating the summarized text based on the identified attributes.

2. The method of claim 1, wherein the identifying of the attributes comprises analyzing one or more of the text and the summarized text.

3. The method of claim 1, wherein the identifying of the attributes comprises detecting an entity name in the analysis units.

4. The method of claim 3, wherein the translating of the summarized text comprises translating the summarized text using the detected entity name.

5. The method of claim 1, wherein the identifying of the attributes comprises:

detecting a category of the summarized text; and

identifying the attributes of the analysis units included in the sentence of the summarized text based on the category.

6. The method of claim 5, wherein the category is determined based on one or more of an Internet address of the text and a received input.

7. The method of claim 1, wherein the identifying of the attributes comprises editing the sentence based on the attributes of the analysis units included in the sentence of the summarized text.

8. The method of claim 7, wherein the editing of the sentence comprises:

deleting or replacing at least one of the analysis units included in the sentence of the summarized text;

or

splitting the sentence of the summarized text.

9. The method of claim 1, wherein the translating of the summarized text comprises translating the summarized text using the identified attributes.

10. The method of claim 9, wherein the translating of the summarized text comprises determining a translation scheme of the analysis units based on the identified attributes.

11. An apparatus for processing text, the apparatus comprising:

a summarization processing unit configured to summarize text by extracting at least one sentence from the text;

an intermediate processing unit configured to identify attributes of analysis units included in the sentence of the summarized text; and

a translation processing unit configured to translate the summarized text based on the identified attributes.

12. The apparatus of claim 11, wherein the intermediate processing unit is configured to analyze one or more of the text and the summarized text.

13. The apparatus of claim 11, wherein the intermediate processing unit is configured to detect an entity name in the analysis units.

14. The apparatus of claim 13, wherein the translation processing unit is configured to translate the summarized text using the detected entity name.

15. The apparatus of claim 11, wherein the intermediate processing unit is configured to detect a category of the summarized text and to identify the attributes of the analysis units included in the sentence of the summarized text based on the category.

16. The apparatus of claim 15, wherein the category is determined based on one or more of an Internet address of the text and a received input.

17. The apparatus of claim 11, wherein the intermediate processing unit is configured to edit the sentence based on the attributes of the analysis units included in the sentence of the summarized text.

18. The apparatus of claim 17, wherein the intermediate processing unit is configured to delete or replace at least one of the analysis units included in the sentence of the summarized text or to split the sentence of the summarized text.

19. The apparatus of claim 11, wherein the translation processing unit is configured to translate the summarized text using the identified attributes.

20. The apparatus of claim 19, wherein the translation processing unit is configured to determine a translation scheme of the analysis units based on the identified attributes.