IP Library › Granted Patent US 11,216,617
Granted Patent B2
US 11,216,617 · App. 16/223,631 · Granted Jan 4, 2022

Methods, computer readable media, and systems for machine translation between Arabic and Arabic sign language

Inventors: Hamzah Luqman (Dhahran, SA); Sabri A. Mahmoud (Dhahran, SA)
Assignee: King Fahd University of Petroleum and Minerals
G06F40/30G06F40/211G06F40/242G06F40/247G06F40/253G06F40/268
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,216,617
App. No.
16/223,631
Granted
Jan 4, 2022
Kind
B2
Abstract

Methods, systems, and computer readable media for machine translation between Arabic language and Arabic Sign Language are described.

Claims (32)

1. A method comprising:

receiving, at a processor, an electronic representation of a first sentence in a first written language;

programmatically performing, using the processor, a morphological analysis of the first sentence to generate a morphological result;

programmatically performing, using the processor, a syntactical analysis of the morphological result to generate a syntactic analysis result;

generating, using the processor, a first dependency tree corresponding to the first sentence in the first written language based on the syntactic analysis result;

receiving, at a second language generation module of the processor, the first dependency tree, one or more transformation rules, a second language dictionary, and a synonym dictionary;

generating, using the second language generation module of the processor, a second dependency tree based on the first dependency tree, one or more transformation rules, the second language dictionary, and the synonym dictionary; and

generating a second sentence in a second written language and a sign language sequence based on the second dependency tree.

2. The method of claim 1 , wherein the first written language is Arabic and the second written language is a gloss notation representation of Arabic Sign Language (ArSL).

3. The method of claim 1 , wherein the sign language sequence includes one or more images representing an Arabic Sign Language (ArSL) sequence.

4. The method of claim 1 , wherein the morphological result includes words of the first sentence along with tagging information associated with one or more of the words of the first sentence.

5. The method of claim 1 , wherein the syntactic analysis result includes a syntax tree.

6. The method of claim 1 , wherein the second language dictionary includes an Arabic Sign Language (ArSL) dictionary.

7. The method of claim 1 , wherein the synonym dictionary includes a semantic database of Arabic words grouped into one or more sets of synonyms.

8. The method of claim 1 , wherein generating the second sentence includes applying one or more transfer rules to map the first written language to the second language.

9. A system comprising:

one or more processors coupled to a non-transitory computer readable medium having stored thereon software instructions that, when executed by the one or more processors, cause the one or more processors to perform operations including:

receiving, at the one or more processors, an electronic representation of a first sentence in a first written language;

programmatically performing, using the one or more processors, a morphological analysis of the first sentence to generate a morphological result;

programmatically performing, using the one or more processors, a syntactical analysis of the morphological result to generate a syntactic analysis result;

generating, using the one or more processors, a first dependency tree corresponding to the first sentence in the first written language based on the syntactic analysis result;

receiving, at a second language generation module of the one or more processors, the first dependency tree, one or more transformation rules, a second language dictionary, and a synonym dictionary;

generating, using the second language generation module of the one or more processors, a second dependency tree based on the first dependency tree, one or more transformation rules, the second language dictionary, and the synonym dictionary; and

generating, using the one or more processors, a second sentence in a second written language and a sign language sequence based on the second dependency tree.

10. The system of claim 9 , wherein the first written language is Arabic and the second written language is a gloss notation representation of Arabic Sign Language (ArSL).

11. The system of claim 9 , wherein the sign language sequence includes one or more images representing an Arabic Sign Language (ArSL) sequence.

12. The system of claim 9 , wherein the morphological result includes words of the first sentence along with tagging information associated with one or more of the words of the first sentence.

13. The system of claim 9 , wherein the syntactic analysis result includes a syntax tree.

14. The system of claim 9 , wherein the second language dictionary includes an Arabic Sign Language (ArSL) dictionary.

15. The system of claim 9 , wherein the synonym dictionary includes a semantic database of Arabic words grouped into one or more sets of synonyms.

16. The system of claim 9 , wherein generating the second sentence includes applying one or more transfer rules to map the first written language to the second language.

17. The system of claim 16 , wherein the transfer rules map Arabic to Arabic sign language.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Dec 18, 2018
From: LUQMAN, HAMZAH; MAHMOUD, SABRI A.
To: KING FAHD UNIVERSITY OF PETROLEUM AND MINERALS
Reel/Frame 047806/0862 →
Continuity (1)
Related Publication 20200192982A1 · Jun 18, 2020