Display assist apparatus, method, and program

• US 10,423,700 B2
• Filed: 02/15/2017
• Issued: 09/24/2019
• Est. Priority Date: 03/16/2016
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Sakamoto, Akiko
• Primary Examiner(s): Tran, Quoc A
• Application Number:
  US15/433,720
• Publication Number:
  US 20170270080A1
• Time in Patent Office: 951 Days
• CPC Class Codes: G06F 40/103 Formatting, i.e. changing of presentation of documents automatic justification G06F40/189; automatic line break hyphenation G06F40/191
• CPC Class Codes: G06F 40/106 Display of layout of documents; Previewing
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G06F 40/30 Semantic analysis
• 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 40/45 Example-based machine translation; Alignment
• CPC Class Codes: G06F 40/47 Machine-assisted translation, e.g. using translation memory
• CPC Class Codes: G06F 40/55 Rule-based translation
• 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
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

According to one embodiment, a display assist apparatus includes an acquisition unit, a first processor, a second processor, and a display controller. The acquisition unit acquires a character string. The first processor divides the character string into first segments each of which is a segment representing a semantic cluster and generates a plurality of divided character strings. The second processor detects, for the character string, second segments each of which is a segment larger than the each of the first segments. The display controller performs display control to make a distinction between the first segments and the second segments when displaying the plurality of divided character strings.

Claims

1. A display assist apparatus comprising:

an acquisition unit configured to acquire a character string which is included in a spoken language;

a first processor configured to divide the character string into first segments each of which is a segment representing a semantic cluster and generate a plurality of divided character strings;

a first adder configured to add a plurality of role labels to first divided character strings of the plurality of divided character strings, the role labels representing roles of the first divided character strings, the roles including pauses used as one of the first segments;

a second processor configured to detect, for the character string, second segments each of which is a segment larger than the each of the first segments;

detect the role labels and an arrangement of the pauses, and determine one of a clause end or a sentence end;

a second adder configured to add a plurality of ending labels to second divided character strings of the plurality of divided character strings at ends of the second segments; and

a display controller configured to perform display control to make a distinction between the first segments and the second segments based on ending labels and an order of the role labels when displaying the plurality of divided character strings.

2. The apparatus according to claim 1, further comprising a convertor configured to convert an expression of the divided character string into another expression based on a conversion rule,

wherein the display controller performs the display control based on the converted divided character string.

3. The apparatus according to claim 1, wherein when displaying the plurality of divided character strings, the display controller performs processing of displaying a second divided character string following a first divided character string with an indent, and if the second divided character string is located at an end of the second segment, the display controller performs processing of displaying a blank line after the second divided character string is displayed.

4. The apparatus according to claim 1, further comprising a machine translator configured to machine-translate the plurality of divided character strings from a first language to a second language,

wherein the display controller performs the display control for the machine-translated divided character strings.

5. The apparatus according to claim 4, further comprising a determiner configured to determine a display order of the plurality of divided character strings based on a word order determination rule of the second language, wherein the display controller performs the display control for the plurality of divided character strings for which the display order is determined.

6. The apparatus according to claim 1, wherein the character string is a character string of a speech recognition result.

7. The apparatus according to claim 1, wherein the first segment is a phrase, and the second segment is one of a clause and a sentence.

8. The apparatus according to claim 1, wherein the first segment is a simple sentence, and the second segment is a compound sentence.

9. The apparatus according to claim 1, wherein the acquisition unit further acquires speaker information of each speaker, and

the display controller performs the display control to make a distinction between the speakers.

10. A display assist method comprising:

acquiring a character string which is included in a spoken language;

dividing the character string into first segments each of which is a segment representing a semantic cluster;

generating a plurality of divided character strings;

adding a plurality of role labels to first divided character strings of the plurality of divided character strings, the role labels representing roles of the first divided character strings, the roles including pauses used as one of the first segments;

detecting, for the character string, second segments each of which is a segment larger than the each of the first segments;

detecting the role labels and an arrangement of the pauses;

determining one of a clause end or a sentence end;

adding a plurality of ending labels to second divided character strings of the plurality of divided character strings at ends of the second segments; and

performing display control to make a distinction between the first segments and the second segments based on ending labels and an order of the role labels when displaying the plurality of divided character strings.

11. A non-transitory computer readable medium storing a computer program which is executed by a computer to provide the steps of:

acquiring a character string which is included in a spoken language;

dividing the character string into first segments each of which is a segment representing a semantic cluster;

generating a plurality of divided character strings;

adding a plurality of role labels to first divided character strings of the plurality of divided character strings, the role labels representing roles of the first divided character strings, the roles including pauses used as one of the first segments;

detecting, for the character string, second segments each of which is a segment larger than the each of the first segments;

detecting the role labels and an arrangement of the pauses;

determining one of a clause end or a sentence end;

adding a plurality of ending labels to second divided character strings of the plurality of divided character strings at ends of the second segments; and

performing display control to make a distinction between the first segments and the second segments based on ending labels and an order of the role labels when displaying the plurality of divided character strings.